REVIEW 2 cited by
Revisiting Over-smoothing in Deep GCNs
Not yet reviewed by Pith; the record is open.
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
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.
Forward citations
Cited by 2 Pith papers
-
M4GN: Mesh-based Multi-segment Hierarchical Graph Network for Dynamic Simulations
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.
-
Anomaly Detection and Early Warning Mechanism for Intelligent Monitoring Systems in Multi-Cloud Environments Based on LLM
A CNN-LSTM-LLM-deep SVM hybrid is proposed for multi-cloud anomaly detection, but the evaluation is qualitative and Equation (8) is mathematically wrong.
Discussion (0). Continue with ORCID to comment.