A Benchmark Dataset for Graph Regression with Homogeneous and Multi-Relational Variants
Not on the map. Why?
Abstract (arXiv)
Graph-level regression underpins many real-world applications, yet public benchmarks remain heavily skewed toward molecular graphs and citation networks. This limited diversity hinders progress on models that must generalize across both homogeneous and heterogeneous graph structures. We introduce RelSC, a new graph-regression dataset built from program graphs that combine syntactic and semantic information extracted from source code. Each graph is labelled with the execution-time cost of the corresponding program, providing a continuous target variable that differs markedly from those found in existing benchmarks. RelSC is released in two complementary variants. RelSC-H supplies rich node features under a single (homogeneous) edge type, while RelSC-M preserves the original multi-relational structure, connecting nodes through multiple edge types that encode distinct semantic relationships. Together, these variants let researchers probe how representation choice influences model behaviour. We evaluate a diverse set of graph neural network architectures on both variants of RelSC. The results reveal consistent performance differences between the homogeneous and multi-relational settings, emphasising the importance of structural representation. These findings demonstrate RelSC's value as a challenging and versatile benchmark for advancing graph regression methods.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 53 of its 102 references that are in the map. First posted on arXiv 29 May 2025.
Builds on
53 of 102 references.
References · 53
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2021Evaluating Large Language Models Trained on Codecited by 8,320
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2017Neural Message Passing for Quantum Chemistrycited by 3,487
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
- 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
- 2019Simplifying Graph Convolutional Networkscited by 1,477
- 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,310
- 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
38 more
- 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
- 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 906
- 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
- 2018Link Prediction Based on Graph Neural Networkscited by 832
- 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
- 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
- 2019Graph Neural Networks for Social Recommendationcited by 714
- 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 609
- 2020Heterogeneous Graph Transformercited by 582
- 2019Graph Transformer Networkscited by 523
- 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
- 2020Principal Neighbourhood Aggregation for Graph Netscited by 478
- 2019Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networkscited by 272
- 2022Long Range Graph Benchmarkcited by 263
- 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 261
- 2018code2vec: Learning Distributed Representations of Codecited by 250
- 2023A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Modelscited by 246
- 2017Learning to Represent Programs with Graphscited by 220
- 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
- 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 149
- 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 138
- 2018Automated Vulnerability Detection in Source Code Using Deep Representation Learningcited by 114
- 2020Contrastive Code Representation Learningcited by 76
- 2022Graph Rationalization with Environment-based Augmentationscited by 70
- 2021DOBF: A Deobfuscation Pre-Training Objective for Programming Languagescited by 68
- 2020Memory-Based Graph Networkscited by 56
- 2022LineVD: Statement-level Vulnerability Detection using Graph Neural Networkscited by 35
- 2021CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Treescited by 32
- 2021ReGVD: Revisiting Graph Neural Networks for Vulnerability Detectioncited by 32
- 2021Heterogeneous Graph Representation Learning with Relation Awarenesscited by 31
- 2023OpenGSL: A Comprehensive Benchmark for Graph Structure Learningcited by 30
- 2023Meta-Path Learning for Multi-relational Graph Neural Networkscited by 10
- 2022Rapid Regression Detection in Software Deployments through Sequential Testingcited by 7
- 2024A Self-Explainable Heterogeneous GNN for Relational Deep Learningcited by 7
- 2022TEP-GNN: Accurate Execution Time Prediction of Functional Tests using Graph Neural Networkscited by 5
- 2023Survey of Malware Analysis through Control Flow Graph using Machine Learningcited by 5
- 2024DFEPT: Data Flow Embedding for Enhancing Pre-Trained Model Based Vulnerability Detectioncited by 4
50 most cited of 53 All 53 (JSON)
Built on by
Not cited yet.