mlsanityData to 14 Oct 2026

On the Topology Awareness and Generalization Performance of Graph Neural Networks

arXiv 2403.04482 ↗First posted 7 Mar 2024cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Many computer vision and machine learning problems are modelled as learning tasks on graphs where graph neural networks GNNs have emerged as a dominant tool for learning representations of graph structured data A key feature of GNNs is their use of graph structures as input enabling them to exploit the graphs inherent topological properties known as the topology awareness of GNNs Despite the empirical successes of GNNs the influence of topology awareness on generalization performance remains unexplored, particularly for node level tasks that diverge from the assumption of data being independent and identically distributed IID The precise definition and characterization of the topology awareness of GNNs especially concerning different topological features are still unclear This paper introduces a comprehensive framework to characterize the topology awareness of GNNs across any topological feature Using this framework we investigate the effects of topology awareness on GNN generalization performance Contrary to the prevailing belief that enhancing the topology awareness of GNNs is always advantageous our analysis reveals a critical insight improving the topology awareness of GNNs may inadvertently lead to unfair generalization across structural groups which might not be desired in some scenarios Additionally we conduct a case study using the intrinsic graph metric the shortest path distance on various benchmark datasets The empirical results of this case study confirm our theoretical insights Moreover we demonstrate the practical applicability of our framework by using it to tackle the cold start problem in graph active learning

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 37 of its 58 references that are in the map. First posted on arXiv 7 Mar 2024.

Builds on

37 of 58 references.

References · 37

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  7. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  8. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  9. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
  10. 2020Simple and Deep Graph Convolutional Networkscited by 860
  11. 2020A Survey of Deep Active Learningcited by 554
  12. 2017Scene Graph Generation by Iterative Message Passingcited by 462
25 more
  1. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 414
  2. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 335
  3. 2016Visual Relationship Detection with Language Priorscited by 334
  4. 2019Position-aware Graph Neural Networkscited by 203
  5. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 164
  6. 2020Towards Deeper Graph Neural Networks with Differentiable Group Normalizationcited by 114
  7. 2020A Survey on The Expressive Power of Graph Neural Networkscited by 111
  8. 2020A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networkscited by 85
  9. 2019Stability and Generalization of Graph Convolutional Neural Networkscited by 81
  10. 2022Fairness in Graph Mining: A Surveycited by 76
  11. 2022Scene Graph Generation: A Comprehensive Surveycited by 73
  12. 2021Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalizationcited by 70
  13. 2021Subgroup Generalization and Fairness of Graph Neural Networkscited by 69
  14. 2017Active Learning for Graph Embeddingcited by 54
  15. 2021Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networkscited by 51
  16. 2020Graph Policy Network for Transferable Active Learning on Graphscited by 50
  17. 2022Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPscited by 42
  18. 2019Active Learning for Graph Neural Networks via Node Feature Propagationcited by 37
  19. 2024Towards Robust Graph Incremental Learning on Evolving Graphscited by 18
  20. 2020GraphReach: Position-Aware Graph Neural Network using Reachability Estimationscited by 14
  21. 2022Partition-Based Active Learning for Graph Neural Networkscited by 12
  22. 2024MSPipe: Efficient Temporal GNN Training via Staleness-Aware Pipelinecited by 12
  23. 2019On the Fairness of Time-Critical Influence Maximization in Social Networkscited by 10
  24. 2024PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networkscited by 10
  25. 2022Structure of Core-Periphery Communitiescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networkscited by 2
  2. 2026Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approachcited by 1
  3. 2026Structuring Relations Among Learning Paradigms via Protocol--Objective--Resource Reductionscited by 0