mlsanityData to 14 Oct 2026

Graph Pooling via Coarsened Graph Infomax

arXiv 2105.01275 ↗First posted 4 May 2021cs.LG cs.AIcited by 15

Not on the map. Why?

Abstract (arXiv)

Graph pooling that summaries the information in a large graph into a compact form is essential in hierarchical graph representation learning. Existing graph pooling methods either suffer from high computational complexity or cannot capture the global dependencies between graphs before and after pooling. To address the problems of existing graph pooling methods, we propose Coarsened Graph Infomax Pooling (CGIPool) that maximizes the mutual information between the input and the coarsened graph of each pooling layer to preserve graph-level dependencies. To achieve mutual information neural maximization, we apply contrastive learning and propose a self-attention-based algorithm for learning positive and negative samples. Extensive experimental results on seven datasets illustrate the superiority of CGIPool comparing to the state-of-the-art methods.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 22 of its 36 references that are in the map. First posted on arXiv 4 May 2021.

Builds on

22 of 36 references.

References · 22

  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. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  5. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  6. 2018Deep Graph Infomaxcited by 1,106
  7. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  8. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  9. 2017Generative Adversarial Networks: An Overviewcited by 590
  10. 2019A Theoretical Analysis of Contrastive Unsupervised Representation Learningcited by 530
  11. 2019Self-Attention Graph Poolingcited by 421
  12. 2015Diffusion-Convolutional Neural Networkscited by 268
10 more
  1. 2019ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representationscited by 156
  2. 2015Training generative neural networks via Maximum Mean Discrepancy optimizationcited by 151
  3. 2020Fairness-Aware Explainable Recommendation over Knowledge Graphscited by 74
  4. 2020Memory-Based Graph Networkscited by 56
  5. 2019Edge Contraction Pooling for Graph Neural Networkscited by 53
  6. 2020VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classificationcited by 35
  7. 2020Graph Cross Networks with Vertex Infomax Poolingcited by 31
  8. 2020Detecting Beneficial Feature Interactions for Recommender Systemscited by 22
  9. 2019Spectral Clustering with Graph Neural Networks for Graph Poolingcited by 16
  10. 2019CBHE: Corner-based Building Height Estimation for Complex Street Scene Imagescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 2; 2024: 5; 2025: 3; 2026: 1.

15 papers.

Sort:

  1. 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
  2. 2022Higher-order Clustering and Pooling for Graph Neural Networkscited by 26
  3. 2024A Topology-aware Graph Coarsening Framework for Continual Graph Learningcited by 11
  4. 2021Neural Graph Matching based Collaborative Filteringcited by 9
  5. 2024Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Trainingcited by 9
  6. 2024A Comprehensive Graph Pooling Benchmark: Effectiveness, Robustness and Generalizabilitycited by 7
  7. 2024MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networkscited by 5
  8. 2023On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Poolingcited by 4
  9. 2022Tackling Provably Hard Representative Selection via Graph Neural Networkscited by 2
  10. 2024Multimodal Physiological Signals Representation Learning via Multiscale Contrasting for Depression Recognitioncited by 2
  11. 2025BN-Pool: Bayesian Nonparametric Pooling for Graphscited by 2
  12. 2025GBGC: Efficient and Adaptive Graph Coarsening via Granular-ball Computingcited by 2
3 more
  1. 2023Careful Selection and Thoughtful Discarding: Graph Explicit Pooling Utilizing Discarded Nodescited by 1
  2. 2025ELPG-DTFS: Prior-Guided Adaptive Time-Frequency Graph Neural Network for EEG Depression Diagnosiscited by 0
  3. 2026Efficient and Scalable Granular-ball Graph Coarsening Method for Large-scale Graph Node Classificationcited by 0