mlsanityData to 7 Oct 2026

Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research

arXiv 2403.08438 ↗First posted 13 Mar 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Difficulties in replication and reproducibility of empirical evidences in machine learning research have become a prominent topic in recent years. Ensuring that machine learning research results are sound and reliable requires reproducibility, which verifies the reliability of research findings using the same code and data. This promotes open and accessible research, robust experimental workflows, and the rapid integration of new findings. Evaluating the degree to which research publications support these different aspects of reproducibility is one goal of the present work. For this we introduce an ontology of reproducibility in machine learning and apply it to methods for graph neural networks. Building on these efforts we turn towards another critical challenge in machine learning, namely the curse of dimensionality, which poses challenges in data collection, representation, and analysis, making it harder to find representative data and impeding the training and inference processes. Using the closely linked concept of geometric intrinsic dimension we investigate to which extend the used machine learning models are influenced by the intrinsic dimension of the data sets they are trained on.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 69 of its 143 references that are in the map. First posted on arXiv 13 Mar 2024.

Builds on

69 of 143 references.

References · 69

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  6. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  7. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  8. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  9. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  10. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  11. 2021E(n) Equivariant Graph Neural Networkscited by 951
  12. 2017A Closer Look at Memorization in Deep Networkscited by 936
38 more
  1. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  2. 2020What Makes for Good Views for Contrastive Learning?cited by 843
  3. 2018Link Prediction Based on Graph Neural Networkscited by 829
  4. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  5. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  6. 2019Heterogeneous Graph Attention Networkcited by 732
  7. 2019Neural Graph Collaborative Filteringcited by 660
  8. 2020Heterogeneous Graph Transformercited by 581
  9. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 565
  10. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  11. 2019Graph Transformer Networkscited by 520
  12. 2018Hypergraph Neural Networkscited by 482
  13. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  14. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 461
  15. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
  16. 2019Self-Attention Graph Poolingcited by 421
  17. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
  18. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  19. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  20. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  21. 2020The Pitfalls of Simplicity Bias in Neural Networkscited by 349
  22. 2018Graph Convolutional Networks for Text Classificationcited by 345
  23. 2019KGAT: Knowledge Graph Attention Network for Recommendationcited by 342
  24. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  25. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 318
  26. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  27. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  28. 2021The Intrinsic Dimension of Images and Its Impact on Learningcited by 307
  29. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  30. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  31. 2020Towards Deeper Graph Neural Networkscited by 296
  32. 2019Intrinsic dimension of data representations in deep neural networkscited by 276
  33. 2018Deep learning generalizes because the parameter-function map is biased towards simple functionscited by 180
  34. 2018Graph Convolution over Pruned Dependency Trees Improves Relation Extractioncited by 146
  35. 2017Encoding Sentences with Graph Convolutional Networks for Semantic Role Labelingcited by 137
  36. 2018DKN: Deep Knowledge-Aware Network for News Recommendationcited by 137
  37. 2022Training Data Influence Analysis and Estimation: A Surveycited by 134
  38. 2020Graph Convolutional Networks for Hyperspectral Image Classificationcited by 113

50 most cited of 69 All 69 (JSON)

Built on by

Not cited yet.