mlsanityData to 14 Oct 2026

Geometric Pooling: maintaining more useful information

arXiv 2306.12341 ↗First posted 21 Jun 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph Pooling technology plays an important role in graph node classification tasks. Sorting pooling technologies maintain large-value units for pooling graphs of varying sizes. However, by analyzing the statistical characteristic of activated units after pooling, we found that a large number of units dropped by sorting pooling are negative-value units that contain useful information and can contribute considerably to the final decision. To maintain more useful information, a novel pooling technology, called Geometric Pooling (GP), was proposed to contain the unique node features with negative values by measuring the similarity of all node features. We reveal the effectiveness of GP from the entropy reduction view. The experiments were conducted on TUdatasets to show the effectiveness of GP. The results showed that the proposed GP outperforms the SOTA graph pooling technologies by 1%~5% with fewer parameters.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 36 references that are in the map. First posted on arXiv 21 Jun 2023.

Builds on

24 of 36 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  5. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  7. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  8. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  9. 2019When Does Label Smoothing Help?cited by 988
  10. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  11. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  12. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
12 more
  1. 2019Graph U-Netscited by 492
  2. 2019Self-Attention Graph Poolingcited by 421
  3. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  4. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 367
  5. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  6. 2015Order Matters: Sequence to sequence for setscited by 237
  7. 2016On Valid Optimal Assignment Kernels and Applications to Graph Classificationcited by 49
  8. 2022QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Querycited by 13
  9. 2021AdaptivePose: Human Parts as Adaptive Pointscited by 6
  10. 2022Learning Quality-aware Representation for Multi-person Pose Regressioncited by 6
  11. 2022AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regressioncited by 6
  12. 2020SPCNet:Spatial Preserve and Content-aware Network for Human Pose Estimationcited by 5

Built on by

Not cited yet.