Methods › Graphs › Graph Models › DiffPool

DiffPool

7 papers tagged archive 2025-07-28

Introduced by Rex Ying et al. in Hierarchical Graph Representation Learning with Differentiable Pooling

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

DiffPool is a differentiable graph pooling module that can generate hierarchical representations of graphs and can be combined with various graph neural network architectures in an end-to-end fashion. DiffPool learns a differentiable soft cluster assignment for nodes at each layer of a deep GNN, mapping nodes to a set of clusters, which then form the coarsened input for the next GNN layer.

Description and image from: Hierarchical Graph Representation Learning with Differentiable Pooling

Paper Source

Papers archive 2025-07-28

7 shown of 7, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tackling Oversmoothing in GNN via Graph Sparsification: A Truss-based Approach
16 Jul 2024 · 0 repositories · arXiv:2407.11928
On Graph Neural Network Ensembles for Large-Scale Molecular Property Prediction
29 Jun 2021 · 1 repository · arXiv:2106.15529
Adaptive Visibility Graph Neural Network and It's Application in Modulation Classification
16 Jun 2021 · 0 repositories · arXiv:2106.08564
GNNIE: GNN Inference Engine with Load-balancing and Graph-Specific Caching
21 May 2021 · 0 repositories · arXiv:2105.10554
SimPool: Towards Topology Based Graph Pooling with Structural Similarity Features
3 Jun 2020 · 0 repositories · arXiv:2006.02244
Pooling in Graph Convolutional Neural Networks
7 Apr 2020 · 0 repositories · arXiv:2004.03519
Hierarchical Graph Representation Learning with Differentiable Pooling
22 Jun 2018 · 14 repositories · arXiv:1806.08804

Syntology ran 1 of 20 samples · 19 unverified

Tasks archive 2025-07-28

19 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Graph Neural Network	5
Graph Classification	4
General Classification	2
Active Learning	1
Avg	1
CPU	1
Classification	1
GPU	1
Graph Attention	1
Graph Representation Learning	1
Link Prediction	1
Molecular Property Prediction	1
Node Classification	1
Prediction	1
Property Prediction	1
Representation Learning	1
Time Series	1
Time Series Analysis	1
graph partitioning	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (7 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Graph Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections