12 Search Results for "Hong, Yu Xuan"

Document
DOI: 10.4230/OASIcs.PARMA-DITAM.2026.8
Performance Modeling & Mapping of LLM Inference on Heterogeneous Vectorized CGRAs

Authors: Dionysios Kefallinos, Georgios Alexandris, Alexis Maras, Panagiotis Chaidos, Manil Dev Gomony, Henk Corporaal, Dimitrios Soudris, and Sotirios Xydis

Published in: OASIcs, Volume 141, 17th Workshop on Parallel Programming and Run-Time Management Techniques for Many-Core Architectures and 15th Workshop on Design Tools and Architectures for Multicore Embedded Computing Platforms (PARMA-DITAM 2026)

Abstract
Since the emergence of transformer-based models, the computational demands for Large Language Model (LLM) inference have been increasing exponentially, primarily due to their compounding parameter sizes, their structural complexity, and the use of non-linear functions. This tendency leads to the necessity of deploying them on low-power edge devices and DNN accelerators, to fuel next-generation agentic AI systems. Coarse-Grained Reconfigurable Architectures (CGRAs) have proven to be a compelling paradigm for edge acceleration, combining the programmability of general-purpose platforms with the high performance and energy efficiency associated with ASICs. In this work, we introduce an end-to-end performance modeling and mapping framework for LLM inference on heterogeneous CGRAs. Our methodology enables rapid exploration of the micro-architectural design space parameters, i.e., the number of processing elements, vector sizes, and memory configurations, by providing an accurate, explainable, and analytical CGRA performance modeling methodology, with an average cycle error of 0.9%. Architecturally, we build upon R-Blocks, a heterogeneous CGRA platform, and extend it to support floating-point arithmetic operations as well as a full-stack compilation and mapping flow for both full (FP32) and quantized (INT8) Llama2 models. The proposed methodology, evaluated on a 22nm technology node, achieves superior peak performance per Watt compared to related works such as REVAMP and CFEACT (1.8× and 2.8× respectively).
Cite as

Dionysios Kefallinos, Georgios Alexandris, Alexis Maras, Panagiotis Chaidos, Manil Dev Gomony, Henk Corporaal, Dimitrios Soudris, and Sotirios Xydis. Performance Modeling & Mapping of LLM Inference on Heterogeneous Vectorized CGRAs. In 17th Workshop on Parallel Programming and Run-Time Management Techniques for Many-Core Architectures and 15th Workshop on Design Tools and Architectures for Multicore Embedded Computing Platforms (PARMA-DITAM 2026). Open Access Series in Informatics (OASIcs), Volume 141, pp. 8:1-8:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@InProceedings{kefallinos_et_al:OASIcs.PARMA-DITAM.2026.8,
  author =	{Kefallinos, Dionysios and Alexandris, Georgios and Maras, Alexis and Chaidos, Panagiotis and Gomony, Manil Dev and Corporaal, Henk and Soudris, Dimitrios and Xydis, Sotirios},
  title =	{{Performance Modeling \& Mapping of LLM Inference on Heterogeneous Vectorized CGRAs}},
  booktitle =	{17th Workshop on Parallel Programming and Run-Time Management Techniques for Many-Core Architectures and 15th Workshop on Design Tools and Architectures for Multicore Embedded Computing Platforms (PARMA-DITAM 2026)},
  pages =	{8:1--8:14},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-416-1},
  ISSN =	{2190-6807},
  year =	{2026},
  volume =	{141},
  editor =	{Baroffio, Davide and Busia, Paola and Denisov, Lev and Shukla, Nitin},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.PARMA-DITAM.2026.8},
  URN =		{urn:nbn:de:0030-drops-256752},
  doi =		{10.4230/OASIcs.PARMA-DITAM.2026.8},
  annote =	{Keywords: Edge AI, LLM, CGRA, Heterogeneous Architectures, Performance Modeling, Hardware Acceleration, Low Power Computing}
}
Document
Research
DOI: 10.4230/TGDK.4.1.1
On the Computational Cost of Knowledge Graph Embeddings

Authors: Victor Charpenay, Mansour Zoubeirou A Mayaki, and Antoine Zimmermann

Published in: TGDK, Volume 4, Issue 1 (2026). Transactions on Graph Data and Knowledge, Volume 4, Issue 1

Abstract
Over a decade, numerous Knowledge Graph Embedding (KGE) models have been designed and evaluated on reference datasets, always with increasing performance. In this paper, we re-evaluate these models with respect to their computational efficiency during training, by estimating the computational cost of the procedure expressed in floating-point operations. We design a cost model based on analytical expressions and apply it on a collection of 20 KGE models, representative of the state-of-the-art. We show that dimensionality or parameter efficiency, used in the literature to compare models with each other, are not suitable to evaluate the true cost of models. Through fixed-budget experiments, a novel approach to evaluate KGE models based on cost estimates, we re-assess the relative performance of model families compared to the state-of-the-art. Bilinear models such as ComplEx underperform with a low computational budget while hyperbolic linear models appear to offer no particular benefit compared to simpler Euclidian models, especially the MuRE model. Neural models, such as ConvE or CompGCN, achieve reasonable performance in the literature but their high computational cost appears unnecessary when compared with other models. The trade-off between efficiency and expressivity of both linear and neural models is to be further explored.
Cite as

Victor Charpenay, Mansour Zoubeirou A Mayaki, and Antoine Zimmermann. On the Computational Cost of Knowledge Graph Embeddings. In Transactions on Graph Data and Knowledge (TGDK), Volume 4, Issue 1, pp. 1:1-1:30, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@Article{charpenay_et_al:TGDK.4.1.1,
  author =	{Charpenay, Victor and Zoubeirou A Mayaki, Mansour and Zimmermann, Antoine},
  title =	{{On the Computational Cost of Knowledge Graph Embeddings}},
  journal =	{Transactions on Graph Data and Knowledge},
  pages =	{1:1--1:30},
  ISSN =	{2942-7517},
  year =	{2026},
  volume =	{4},
  number =	{1},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/TGDK.4.1.1},
  URN =		{urn:nbn:de:0030-drops-256863},
  doi =		{10.4230/TGDK.4.1.1},
  annote =	{Keywords: Knowledge Graph Embedding, Parameter Efficiency, Computational Budget, Green AI}
}
Document
DOI: 10.4230/OASIcs.NINeS.2026.13
In-Kernel Aggregation and Broadcast Acceleration for Distributed Communication

Authors: Jianchang Su, Yifan Zhang, and Wei Zhang

Published in: OASIcs, Volume 139, 1st New Ideas in Networked Systems (NINeS 2026)

Abstract
Broadcasting and aggregation dominate the communication overhead in distributed systems, from machine learning training to data analytics. Current acceleration approaches require specialized hardware (RDMA) or dedicated resources (DPDK), limiting their deployment in commodity clouds. However, we present a counter-intuitive alternative: rather than bypassing the kernel, we move operations into it using eBPF. While this imposes severe constraints including no floating-point, limited memory, and stateless execution, we show these restrictions paradoxically drive innovative protocol designs that yield unexpected benefits. We introduce AggBox, which implements broadcast and aggregation operations entirely within eBPF’s constrained environment. Our key innovations include stateless group acknowledgments for reliability, edge quantization for floating-point aggregation using only integer arithmetic, and tail-call chains that create virtual memory beyond eBPF’s 512-byte stack limit. These designs emerge from and exploit the constraints rather than fighting them. AggBox achieves remarkable performance on commodity hardware: 84.5% reduction in broadcast latency, 43× speedup for MapReduce workloads, and 56.1% faster ML gradient aggregation, all without specialized NICs or dedicated cores. Beyond performance, our work demonstrates that constrained environments can drive fundamental innovation in protocol design, offering insights for future resource-limited and verified systems.
Cite as

Jianchang Su, Yifan Zhang, and Wei Zhang. In-Kernel Aggregation and Broadcast Acceleration for Distributed Communication. In 1st New Ideas in Networked Systems (NINeS 2026). Open Access Series in Informatics (OASIcs), Volume 139, pp. 13:1-13:23, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@InProceedings{su_et_al:OASIcs.NINeS.2026.13,
  author =	{Su, Jianchang and Zhang, Yifan and Zhang, Wei},
  title =	{{In-Kernel Aggregation and Broadcast Acceleration for Distributed Communication}},
  booktitle =	{1st New Ideas in Networked Systems (NINeS 2026)},
  pages =	{13:1--13:23},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-414-7},
  ISSN =	{2190-6807},
  year =	{2026},
  volume =	{139},
  editor =	{Argyraki, Katerina and Panda, Aurojit},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.NINeS.2026.13},
  URN =		{urn:nbn:de:0030-drops-255981},
  doi =		{10.4230/OASIcs.NINeS.2026.13},
  annote =	{Keywords: eBPF, distributed communication, broadcast, aggregation, in-kernel processing, XDP}
}
Document
DOI: 10.4230/OASIcs.NINeS.2026.18
TURBO: Utility-Aware Bandwidth Allocation for Cloud-Augmented Autonomous Control

Authors: Peter Schafhalter, Alexander Krentsel, Hongbo Wei, Joseph E. Gonzalez, Sylvia Ratnasamy, Scott Shenker, and Ion Stoica

Published in: OASIcs, Volume 139, 1st New Ideas in Networked Systems (NINeS 2026)

Abstract
Autonomous driving system progress has been driven by improvements in machine learning (ML) models, whose computational demands now exceed what edge devices alone can provide. The cloud offers abundant compute, but the network has long been treated as an unreliable bottleneck rather than a co-equal part of the autonomous vehicle control loop. We argue that this separation is no longer tenable: safety-critical autonomy requires co-design of control, models, and network resource allocation itself. We introduce TURBO, a cloud-augmented control framework that addresses this challenge, formulating bandwidth allocation and control pipeline configuration across both the car and cloud as a joint optimization problem. TURBO maximizes benefit to the car while guaranteeing safety in the face of highly variable network conditions. We implement TURBO and evaluate it in both simulation and real-world deployment, showing it can improve average accuracy by up to 15.6%pt over existing on-vehicle-only pipelines. Our code is made available at www.github.com/NetSys/turbo.
Cite as

Peter Schafhalter, Alexander Krentsel, Hongbo Wei, Joseph E. Gonzalez, Sylvia Ratnasamy, Scott Shenker, and Ion Stoica. TURBO: Utility-Aware Bandwidth Allocation for Cloud-Augmented Autonomous Control. In 1st New Ideas in Networked Systems (NINeS 2026). Open Access Series in Informatics (OASIcs), Volume 139, pp. 18:1-18:34, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@InProceedings{schafhalter_et_al:OASIcs.NINeS.2026.18,
  author =	{Schafhalter, Peter and Krentsel, Alexander and Wei, Hongbo and Gonzalez, Joseph E. and Ratnasamy, Sylvia and Shenker, Scott and Stoica, Ion},
  title =	{{TURBO: Utility-Aware Bandwidth Allocation for Cloud-Augmented Autonomous Control}},
  booktitle =	{1st New Ideas in Networked Systems (NINeS 2026)},
  pages =	{18:1--18:34},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-414-7},
  ISSN =	{2190-6807},
  year =	{2026},
  volume =	{139},
  editor =	{Argyraki, Katerina and Panda, Aurojit},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.NINeS.2026.18},
  URN =		{urn:nbn:de:0030-drops-256039},
  doi =		{10.4230/OASIcs.NINeS.2026.18},
  annote =	{Keywords: autonomous vehicles, bandwidth allocation, cloud computing, edge computing, machine learning}
}
Document
DOI: 10.4230/OASIcs.NINeS.2026.24
SwiftQueue: Optimizing Low-Latency Applications with Swift Packet Queuing

Authors: Siddhant Ray, Xi Jiang, Jack Luo, Nick Feamster, and Junchen Jiang

Published in: OASIcs, Volume 139, 1st New Ideas in Networked Systems (NINeS 2026)

Abstract
Low Latency, Low Loss, and Scalable Throughput (L4S), as an emerging router-queue management technique, has seen steady deployment in the industry. An L4S-enabled router assigns each packet to the queue based on the packet header marking. Currently, L4S employs per-flow queue selection, i.e., all packets of a flow are marked the same way and thus use the same queues, even though each packet is marked separately. However, this may hurt tail latency and latency-sensitive applications because transient congestion and queue buildups may only affect a fraction of packets in a flow. We present SwiftQueue, a new L4S queue-selection strategy in which a sender uses a novel per-packet latency predictor to pinpoint which packets likely have latency spikes or drops. The insight is that many packet-level latency variations result from complex interactions among recent packets at shared router queues. Yet, these intricate packet-level latency patterns are hard to learn efficiently by traditional models. Instead, SwiftQueue uses a custom Transformer, which is well-studied for its expressiveness on sequential patterns, to predict the next packet’s latency based on the latencies of recently received ACKs. Based on the predicted latency of each outgoing packet, SwiftQueue’s sender dynamically marks the L4S packet header to assign packets to potentially different queues, even within the same flow. Using real network traces, we show that SwiftQueue is 45-65% more accurate in predicting latency and its variations than state-of-art methods. Based on its latency prediction, SwiftQueue reduces the tail latency for L4S-enabled flows by 36-45%, compared with the existing L4S queue-selection method.
Cite as

Siddhant Ray, Xi Jiang, Jack Luo, Nick Feamster, and Junchen Jiang. SwiftQueue: Optimizing Low-Latency Applications with Swift Packet Queuing. In 1st New Ideas in Networked Systems (NINeS 2026). Open Access Series in Informatics (OASIcs), Volume 139, pp. 24:1-24:29, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@InProceedings{ray_et_al:OASIcs.NINeS.2026.24,
  author =	{Ray, Siddhant and Jiang, Xi and Luo, Jack and Feamster, Nick and Jiang, Junchen},
  title =	{{SwiftQueue: Optimizing Low-Latency Applications with Swift Packet Queuing}},
  booktitle =	{1st New Ideas in Networked Systems (NINeS 2026)},
  pages =	{24:1--24:29},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-414-7},
  ISSN =	{2190-6807},
  year =	{2026},
  volume =	{139},
  editor =	{Argyraki, Katerina and Panda, Aurojit},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.NINeS.2026.24},
  URN =		{urn:nbn:de:0030-drops-256093},
  doi =		{10.4230/OASIcs.NINeS.2026.24},
  annote =	{Keywords: Latency prediction, L4S Queue Management}
}
Document
Survey
DOI: 10.4230/TGDK.3.2.1
Resilience in Knowledge Graph Embeddings

Authors: Arnab Sharma, N'Dah Jean Kouagou, and Axel-Cyrille Ngonga Ngomo

Published in: TGDK, Volume 3, Issue 2 (2025). Transactions on Graph Data and Knowledge, Volume 3, Issue 2

Abstract
In recent years, knowledge graphs have gained interest and witnessed widespread applications in various domains, such as information retrieval, question-answering, recommendation systems, amongst others. Large-scale knowledge graphs to this end have demonstrated their utility in effectively representing structured knowledge. To further facilitate the application of machine learning techniques, knowledge graph embedding models have been developed. Such models can transform entities and relationships within knowledge graphs into vectors. However, these embedding models often face challenges related to noise, missing information, distribution shift, adversarial attacks, etc. This can lead to sub-optimal embeddings and incorrect inferences, thereby negatively impacting downstream applications. While the existing literature has focused so far on adversarial attacks on KGE models, the challenges related to the other critical aspects remain unexplored. In this paper, we, first of all, give a unified definition of resilience, encompassing several factors such as generalisation, in-distribution generalization, distribution adaption, and robustness. After formalizing these concepts for machine learning in general, we define them in the context of knowledge graphs. To find the gap in the existing works on resilience in the context of knowledge graphs, we perform a systematic survey, taking into account all these aspects mentioned previously. Our survey results show that most of the existing works focus on a specific aspect of resilience, namely robustness. After categorizing such works based on their respective aspects of resilience, we discuss the challenges and future research directions.
Cite as

Arnab Sharma, N'Dah Jean Kouagou, and Axel-Cyrille Ngonga Ngomo. Resilience in Knowledge Graph Embeddings. In Transactions on Graph Data and Knowledge (TGDK), Volume 3, Issue 2, pp. 1:1-1:38, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@Article{sharma_et_al:TGDK.3.2.1,
  author =	{Sharma, Arnab and Kouagou, N'Dah Jean and Ngomo, Axel-Cyrille Ngonga},
  title =	{{Resilience in Knowledge Graph Embeddings}},
  journal =	{Transactions on Graph Data and Knowledge},
  pages =	{1:1--1:38},
  ISSN =	{2942-7517},
  year =	{2025},
  volume =	{3},
  number =	{2},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/TGDK.3.2.1},
  URN =		{urn:nbn:de:0030-drops-248117},
  doi =		{10.4230/TGDK.3.2.1},
  annote =	{Keywords: Knowledge graphs, Resilience, Robustness}
}
Document
DOI: 10.4230/LIPIcs.DNA.31.11
Leakless Polymerase-Dependent Strand Displacement Systems

Authors: Zoë Evelyn Mōhalakealoha Derauf and Chris Thachuk

Published in: LIPIcs, Volume 347, 31st International Conference on DNA Computing and Molecular Programming (DNA 31) (2025)

Abstract
A grand challenge facing molecular programmers is the rational development of fast, robust, and isothermal architectures akin to "chemical central processing units" that can sense (bio-)chemical signals from their environment, perform complex computation, and orchestrate a physical response in situ. DNA strand displacement systems (DSDs) remain a compelling candidate, but are hampered by spurious reaction pathways that lead to incorrect output. DSDs that utilize the systematic leakless motif can be made arbitrarily robust at the cost of increasing redundancy and network size (scaling), and thus a degradation of kinetic performance. Another class of architectures utilize DNA hybridization, extension, and signal production of entirely sequestered outputs via strand-displacing polymerases (SDPs) that have resulted in impressive demonstrations; however, they face similar challenges of aberrant behavior such as mis-priming by incorrect signals. Our work introduces a unified polymerase-dependent toehold-mediated strand displacement (PD-TMSD) architecture that integrates the programmed specificity of DSDs with the unique advantages of SDPs. This unification enables systems that can be made arbitrarily robust, at any concentration range, without increasing network size. We propose a number of gate designs and composition rules to compute arbitrary Boolean functions, emulate arbitrary chemical reaction networks, and explore time-bounded probabilistic computation made possible by certain classes of SDPs. Our theoretical exploration is backed by preliminary experimental demonstrations. This contribution was inspired by the belief that molecular programming can meet or exceed the complexity exhibited in biology if we embrace its best understood molecular machinery and couple it with systematic design principles built upon a strong theoretical foundation.
Cite as

Zoë Evelyn Mōhalakealoha Derauf and Chris Thachuk. Leakless Polymerase-Dependent Strand Displacement Systems. In 31st International Conference on DNA Computing and Molecular Programming (DNA 31). Leibniz International Proceedings in Informatics (LIPIcs), Volume 347, pp. 11:1-11:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{derauf_et_al:LIPIcs.DNA.31.11,
  author =	{Derauf, Zo\"{e} Evelyn M\={o}halakealoha and Thachuk, Chris},
  title =	{{Leakless Polymerase-Dependent Strand Displacement Systems}},
  booktitle =	{31st International Conference on DNA Computing and Molecular Programming (DNA 31)},
  pages =	{11:1--11:19},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-399-7},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{347},
  editor =	{Schaeffer, Josie and Zhang, Fei},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.DNA.31.11},
  URN =		{urn:nbn:de:0030-drops-238608},
  doi =		{10.4230/LIPIcs.DNA.31.11},
  annote =	{Keywords: DNA strand displacement, strand-displacing polymerases, molecular computation, energy barriers, kinetics}
}
Document
DOI: 10.4230/LIPIcs.GIScience.2025.3
Enriching Location Representation with Detailed Semantic Information

Authors: Junyuan Liu, Xinglei Wang, and Tao Cheng

Published in: LIPIcs, Volume 346, 13th International Conference on Geographic Information Science (GIScience 2025)

Abstract
Spatial representations that capture both structural and semantic characteristics of urban environments are essential for urban modeling. Traditional spatial embeddings often prioritize spatial proximity while underutilizing fine-grained contextual information from places. To address this limitation, we introduce CaLLiPer+, an extension of the CaLLiPer model that systematically integrates Point-of-Interest (POI) names alongside categorical labels within a multimodal contrastive learning framework. We evaluate its effectiveness on two downstream tasks - land use classification and socioeconomic status distribution mapping - demonstrating consistent performance gains of 4% to 11% over baseline methods. Additionally, we show that incorporating POI names enhances location retrieval, enabling models to capture complex urban concepts with greater precision. Ablation studies further reveal the complementary role of POI names and the advantages of leveraging pretrained text encoders for spatial representations. Overall, our findings highlight the potential of integrating fine-grained semantic attributes and multimodal learning techniques to advance the development of urban foundation models.
Cite as

Junyuan Liu, Xinglei Wang, and Tao Cheng. Enriching Location Representation with Detailed Semantic Information. In 13th International Conference on Geographic Information Science (GIScience 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 346, pp. 3:1-3:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{liu_et_al:LIPIcs.GIScience.2025.3,
  author =	{Liu, Junyuan and Wang, Xinglei and Cheng, Tao},
  title =	{{Enriching Location Representation with Detailed Semantic Information}},
  booktitle =	{13th International Conference on Geographic Information Science (GIScience 2025)},
  pages =	{3:1--3:15},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-378-2},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{346},
  editor =	{Sila-Nowicka, Katarzyna and Moore, Antoni and O'Sullivan, David and Adams, Benjamin and Gahegan, Mark},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.GIScience.2025.3},
  URN =		{urn:nbn:de:0030-drops-238322},
  doi =		{10.4230/LIPIcs.GIScience.2025.3},
  annote =	{Keywords: Location Embedding, Contrastive Learning, Pretrained Model}
}
Document
DOI: 10.4230/LIPIcs.ECOOP.2025.6
Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories

Authors: Tianyu Chen, Zeyu Wang, Lin Li, Ding Li, Zongyang Li, Xiaoning Chang, Pan Bian, Guangtai Liang, Qianxiang Wang, and Tao Xie

Published in: LIPIcs, Volume 333, 39th European Conference on Object-Oriented Programming (ECOOP 2025)

Abstract
Functionality-specific vulnerabilities, which mainly occur in Application Programming Interfaces (APIs) with specific functionalities, are crucial for software developers to detect and avoid. When detecting individual functionality-specific vulnerabilities, the existing two categories of approaches are ineffective because they consider only the API bodies and are unable to handle diverse implementations of functionality-equivalent APIs. To effectively detect functionality-specific vulnerabilities, we propose APISS, the first approach to utilize API doc strings and signatures instead of API bodies. APISS first retrieves functionality-equivalent APIs for APIs with existing vulnerabilities and then migrates Proof-of-Concepts (PoCs) of the existing vulnerabilities for newly detected vulnerable APIs. To retrieve functionality-equivalent APIs, we leverage a Large Language Model for API embedding to improve the accuracy and address the effectiveness and scalability issues suffered by the existing approaches. To migrate PoCs of the existing vulnerabilities for newly detected vulnerable APIs, we design a semi-automatic schema to substantially reduce manual costs. We conduct a comprehensive evaluation to empirically compare APISS with four state-of-the-art approaches of detecting vulnerabilities and two state-of-the-art approaches of retrieving functionality-equivalent APIs. The evaluation subjects include 180 widely used Java repositories using 10 existing vulnerabilities, along with their PoCs. The results show that APISS effectively retrieves functionality-equivalent APIs, achieving a Top-1 Accuracy of 0.81 while the best of the baselines under comparison achieves only 0.55. APISS is highly efficient: the manual costs are within 10 minutes per vulnerability and the end-to-end runtime overhead of testing one candidate API is less than 2 hours. APISS detects 179 new vulnerabilities and receives 60 new CVE IDs, bringing high value to security practice.
Cite as

Tianyu Chen, Zeyu Wang, Lin Li, Ding Li, Zongyang Li, Xiaoning Chang, Pan Bian, Guangtai Liang, Qianxiang Wang, and Tao Xie. Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories. In 39th European Conference on Object-Oriented Programming (ECOOP 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 333, pp. 6:1-6:27, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{chen_et_al:LIPIcs.ECOOP.2025.6,
  author =	{Chen, Tianyu and Wang, Zeyu and Li, Lin and Li, Ding and Li, Zongyang and Chang, Xiaoning and Bian, Pan and Liang, Guangtai and Wang, Qianxiang and Xie, Tao},
  title =	{{Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories}},
  booktitle =	{39th European Conference on Object-Oriented Programming (ECOOP 2025)},
  pages =	{6:1--6:27},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-373-7},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{333},
  editor =	{Aldrich, Jonathan and Silva, Alexandra},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECOOP.2025.6},
  URN =		{urn:nbn:de:0030-drops-232999},
  doi =		{10.4230/LIPIcs.ECOOP.2025.6},
  annote =	{Keywords: Application Security, Vulnerability Detection, Large Language Model}
}
Document
Survey
DOI: 10.4230/TGDK.1.1.4
Knowledge Graph Embeddings: Open Challenges and Opportunities

Authors: Russa Biswas, Lucie-Aimée Kaffee, Michael Cochez, Stefania Dumbrava, Theis E. Jendal, Matteo Lissandrini, Vanessa Lopez, Eneldo Loza Mencía, Heiko Paulheim, Harald Sack, Edlira Kalemi Vakaj, and Gerard de Melo

Published in: TGDK, Volume 1, Issue 1 (2023): Special Issue on Trends in Graph Data and Knowledge. Transactions on Graph Data and Knowledge, Volume 1, Issue 1

Abstract
While Knowledge Graphs (KGs) have long been used as valuable sources of structured knowledge, in recent years, KG embeddings have become a popular way of deriving numeric vector representations from them, for instance, to support knowledge graph completion and similarity search. This study surveys advances as well as open challenges and opportunities in this area. For instance, the most prominent embedding models focus primarily on structural information. However, there has been notable progress in incorporating further aspects, such as semantics, multi-modal, temporal, and multilingual features. Most embedding techniques are assessed using human-curated benchmark datasets for the task of link prediction, neglecting other important real-world KG applications. Many approaches assume a static knowledge graph and are unable to account for dynamic changes. Additionally, KG embeddings may encode data biases and lack interpretability. Overall, this study provides an overview of promising research avenues to learn improved KG embeddings that can address a more diverse range of use cases.
Cite as

Russa Biswas, Lucie-Aimée Kaffee, Michael Cochez, Stefania Dumbrava, Theis E. Jendal, Matteo Lissandrini, Vanessa Lopez, Eneldo Loza Mencía, Heiko Paulheim, Harald Sack, Edlira Kalemi Vakaj, and Gerard de Melo. Knowledge Graph Embeddings: Open Challenges and Opportunities. In Special Issue on Trends in Graph Data and Knowledge. Transactions on Graph Data and Knowledge (TGDK), Volume 1, Issue 1, pp. 4:1-4:32, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@Article{biswas_et_al:TGDK.1.1.4,
  author =	{Biswas, Russa and Kaffee, Lucie-Aim\'{e}e and Cochez, Michael and Dumbrava, Stefania and Jendal, Theis E. and Lissandrini, Matteo and Lopez, Vanessa and Menc{\'\i}a, Eneldo Loza and Paulheim, Heiko and Sack, Harald and Vakaj, Edlira Kalemi and de Melo, Gerard},
  title =	{{Knowledge Graph Embeddings: Open Challenges and Opportunities}},
  journal =	{Transactions on Graph Data and Knowledge},
  pages =	{4:1--4:32},
  year =	{2023},
  volume =	{1},
  number =	{1},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/TGDK.1.1.4},
  URN =		{urn:nbn:de:0030-drops-194783},
  doi =		{10.4230/TGDK.1.1.4},
  annote =	{Keywords: Knowledge Graphs, KG embeddings, Link prediction, KG applications}
}
Document
Vision
DOI: 10.4230/TGDK.1.1.8
Machine Learning and Knowledge Graphs: Existing Gaps and Future Research Challenges

Authors: Claudia d'Amato, Louis Mahon, Pierre Monnin, and Giorgos Stamou

Published in: TGDK, Volume 1, Issue 1 (2023): Special Issue on Trends in Graph Data and Knowledge. Transactions on Graph Data and Knowledge, Volume 1, Issue 1

Abstract
The graph model is nowadays largely adopted to model a wide range of knowledge and data, spanning from social networks to knowledge graphs (KGs), representing a successful paradigm of how symbolic and transparent AI can scale on the World Wide Web. However, due to their unprecedented volume, they are generally tackled by Machine Learning (ML) and mostly numeric based methods such as graph embedding models (KGE) and deep neural networks (DNNs). The latter methods have been proved lately very efficient, leading the current AI spring. In this vision paper, we introduce some of the main existing methods for combining KGs and ML, divided into two categories: those using ML to improve KGs, and those using KGs to improve results on ML tasks. From this introduction, we highlight research gaps and perspectives that we deem promising and currently under-explored for the involved research communities, spanning from KG support for LLM prompting, integration of KG semantics in ML models to symbol-based methods, interpretability of ML models, and the need for improved benchmark datasets. In our opinion, such perspectives are stepping stones in an ultimate view of KGs as central assets for neuro-symbolic and explainable AI.
Cite as

Claudia d'Amato, Louis Mahon, Pierre Monnin, and Giorgos Stamou. Machine Learning and Knowledge Graphs: Existing Gaps and Future Research Challenges. In Special Issue on Trends in Graph Data and Knowledge. Transactions on Graph Data and Knowledge (TGDK), Volume 1, Issue 1, pp. 8:1-8:35, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@Article{damato_et_al:TGDK.1.1.8,
  author =	{d'Amato, Claudia and Mahon, Louis and Monnin, Pierre and Stamou, Giorgos},
  title =	{{Machine Learning and Knowledge Graphs: Existing Gaps and Future Research Challenges}},
  journal =	{Transactions on Graph Data and Knowledge},
  pages =	{8:1--8:35},
  year =	{2023},
  volume =	{1},
  number =	{1},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/TGDK.1.1.8},
  URN =		{urn:nbn:de:0030-drops-194824},
  doi =		{10.4230/TGDK.1.1.8},
  annote =	{Keywords: Graph-based Learning, Knowledge Graph Embeddings, Large Language Models, Explainable AI, Knowledge Graph Completion \& Curation}
}
Document
Multimedia Exposition
DOI: 10.4230/LIPIcs.SoCG.2018.76
Star Unfolding of Boxes (Multimedia Exposition)

Authors: Dani Demas, Satyan L. Devadoss, and Yu Xuan Hong

Published in: LIPIcs, Volume 99, 34th International Symposium on Computational Geometry (SoCG 2018)

Abstract
Given a convex polyhedron, the star unfolding of its surface is obtained by cutting along the shortest paths from a fixed source point to each of its vertices. We present an interactive application that visualizes the star unfolding of a box, such that its dimensions and source point locations can be continuously toggled by the user.
Cite as

Dani Demas, Satyan L. Devadoss, and Yu Xuan Hong. Star Unfolding of Boxes (Multimedia Exposition). In 34th International Symposium on Computational Geometry (SoCG 2018). Leibniz International Proceedings in Informatics (LIPIcs), Volume 99, pp. 76:1-76:4, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)

Copy BibTex To Clipboard

@InProceedings{demas_et_al:LIPIcs.SoCG.2018.76,
  author =	{Demas, Dani and Devadoss, Satyan L. and Hong, Yu Xuan},
  title =	{{Star Unfolding of Boxes}},
  booktitle =	{34th International Symposium on Computational Geometry (SoCG 2018)},
  pages =	{76:1--76:4},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-066-8},
  ISSN =	{1868-8969},
  year =	{2018},
  volume =	{99},
  editor =	{Speckmann, Bettina and T\'{o}th, Csaba D.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.SoCG.2018.76},
  URN =		{urn:nbn:de:0030-drops-87890},
  doi =		{10.4230/LIPIcs.SoCG.2018.76},
  annote =	{Keywords: star unfolding, source unfolding, Voronoi diagram}
}
  • Refine by Type
  • 12 Document/PDF
  • 10 Document/HTML

  • Refine by Publication Year
  • 5 2026
  • 4 2025
  • 2 2023
  • 1 2018

  • Refine by Author
  • 1 Alexandris, Georgios
  • 1 Bian, Pan
  • 1 Biswas, Russa
  • 1 Chaidos, Panagiotis
  • 1 Chang, Xiaoning
  • Show More...

  • Refine by Series/Journal
  • 4 LIPIcs
  • 4 OASIcs
  • 4 TGDK

  • Refine by Classification
  • 2 Computing methodologies → Machine learning approaches
  • 2 Computing methodologies → Semantic networks
  • 1 Applied computing → Chemistry
  • 1 Computer systems organization → Distributed architectures
  • 1 Computer systems organization → Embedded and cyber-physical systems
  • Show More...

  • Refine by Keyword
  • 1 Application Security
  • 1 CGRA
  • 1 Computational Budget
  • 1 Contrastive Learning
  • 1 DNA strand displacement
  • Show More...

Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact