mlsanityData to 14 Oct 2026

Learning From Graph-Structured Data: Addressing Design Issues and Exploring Practical Applications in Graph Representation Learning

arXiv 2411.07269 ↗First posted 9 Nov 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Graphs serve as fundamental descriptors for systems composed of interacting elements, capturing a wide array of data types, from molecular interactions to social networks and knowledge graphs. In this paper, we present an exhaustive review of the latest advancements in graph representation learning and Graph Neural Networks (GNNs). GNNs, tailored to handle graph-structured data, excel in deriving insights and predictions from intricate relational information, making them invaluable for tasks involving such data. Graph representation learning, a pivotal approach in analyzing graph-structured data, facilitates numerous downstream tasks and applications across machine learning, data mining, biomedicine, and healthcare. Our work delves into the capabilities of GNNs, examining their foundational designs and their application in addressing real-world challenges. We introduce a GNN equipped with an advanced high-order pooling function, adept at capturing complex node interactions within graph-structured data. This pooling function significantly enhances the GNN's efficacy in both node- and graph-level tasks. Additionally, we propose a molecular graph generative model with a GNN as its core framework. This GNN backbone is proficient in learning invariant and equivariant molecular characteristics. Employing these features, the molecular graph generative model is capable of simultaneously learning and generating molecular graphs with atom-bond structures and precise atom positions. Our models undergo thorough experimental evaluations and comparisons with established methods, showcasing their superior performance in addressing diverse real-world challenges with various datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 56 of its 91 references that are in the map. First posted on arXiv 9 Nov 2024.

Builds on

56 of 91 references.

References · 56

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  7. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  9. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  10. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  11. 2016Variational Graph Auto-Encoderscited by 1,382
  12. 2021Variational Diffusion Modelscited by 1,153
38 more
  1. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  2. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  3. 2020Benchmarking Graph Neural Networkscited by 680
  4. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 677
  5. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  6. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
  7. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
  8. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 520
  9. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 516
  10. 2020Principal Neighbourhood Aggregation for Graph Netscited by 478
  11. 2017Representation Learning on Graphs: Methods and Applicationscited by 457
  12. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  13. 2017Residual Gated Graph ConvNetscited by 346
  14. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 275
  15. 2019Cormorant: Covariant Molecular Neural Networkscited by 263
  16. 2021GRAND: Graph Neural Diffusioncited by 258
  17. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 250
  18. 2020DeeperGCN: All You Need to Train Deeper GCNscited by 250
  19. 2020Can Graph Neural Networks Count Substructures?cited by 236
  20. 2023Geometric Latent Diffusion Models for 3D Molecule Generationcited by 186
  21. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 185
  22. 2022TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentialscited by 182
  23. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 172
  24. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  25. 2021E(n) Equivariant Normalizing Flowscited by 165
  26. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  27. 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
  28. 2022One Transformer Can Understand Both 2D & 3D Molecular Datacited by 77
  29. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
  30. 2019Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networkscited by 62
  31. 2023MUDiff: Unified Diffusion for Complete Molecule Generationcited by 42
  32. 2021Top-N: Equivariant set and graph generation without exchangeabilitycited by 36
  33. 2024The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challengescited by 29
  34. 2020Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designscited by 25
  35. 2022High-Order Pooling for Graph Neural Networks with Tensor Decompositioncited by 24
  36. 2017Tensor Regression Networks with various Low-Rank Tensor Approximationscited by 8
  37. 2021Parameterized Hypercomplex Graph Neural Networks for Graph Classificationcited by 7
  38. 2023When Do Graph Neural Networks Help with Node Classification? Investigating the Impact of Homophily Principle on Node Distinguishabilitycited by 7

50 most cited of 56 All 56 (JSON)

Built on by

Not cited yet.