Pith. sign in

REVIEW 6 cited by

Revisiting Over-smoothing in Deep GCNs

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2003.13663 v5 pith:PB6NUAPN submitted 2020-03-30 cs.LG stat.ML

Chaoqi Yang , Ruijie Wang , Shuochao Yao , Shengzhong Liu , Tarek Abdelzaher This is my paper
classification cs.LGstat.ML
keywords deepgcnstrainingduringfurthergraphnetworkstrick
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Oversmoothing has been assumed to be the major cause of performance drop in deep graph convolutional networks (GCNs). In this paper, we propose a new view that deep GCNs can actually learn to anti-oversmooth during training. This work interprets a standard GCN architecture as layerwise integration of a Multi-layer Perceptron (MLP) and graph regularization. We analyze and conclude that before training, the final representation of a deep GCN does over-smooth, however, it learns anti-oversmoothing during training. Based on the conclusion, the paper further designs a cheap but effective trick to improve GCN training. We verify our conclusions and evaluate the trick on three citation networks and further provide insights on neighborhood aggregation in GCNs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Concept Graph Convolutions: Message Passing in the Concept Space

    cs.LG 2026-04 unverdicted novelty 7.0 of 10

    Concept Graph Convolutions perform message passing on node concepts to increase interpretability of graph neural networks without losing task performance.

  2. NSPOD: Accelerating Krylov solvers via DeepONet-learned POD subspaces

    math.NA 2026-05 unverdicted novelty 6.0 of 10

    NSPOD is a multigrid-like deep operator network preconditioner that dramatically reduces Krylov solver iterations for linearized solid mechanics PDEs on unstructured meshes from CAD geometries.

  3. NSPOD: Accelerating Krylov solvers via DeepONet-learned POD subspaces

    math.NA 2026-05 unverdicted novelty 6.0 of 10

    NSPOD is a multigrid-like preconditioner using DeepONet-learned POD subspaces that dramatically cuts Krylov solver iterations for solid mechanics PDEs on unstructured CAD geometries, outperforming algebraic multigrid.

  4. How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation

    cs.LG 2025-11 unverdicted novelty 6.0 of 10

    C3E estimates hidden dimensions and depths for GNNs by treating them as communication channels to reduce over-squashing and improve representation learning.

  5. Differential-Integral Neural Operator for Long-Term Turbulence Forecasting

    cs.LG 2025-09 unverdicted novelty 6.0 of 10

    DINO decomposes turbulent evolution into parallel local differential and global integral operators to achieve stable autoregressive forecasting on 2D Kolmogorov flow.

  6. M4GN: Mesh-based Multi-segment Hierarchical Graph Network for Dynamic Simulations

    cs.LG 2025-09 conditional novelty 6.0 of 10

    A hierarchical mesh-graph network with modal-decomposition-guided segmentation reports up to 56% lower rollout error than baselines and introduces a long-range beam-deformation benchmark.

Pith tools