Pith. sign in

REVIEW 1 cited by

Graph convolutions that can finally model local structure

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

arxiv 2011.15069 v2 pith:MIHP5UBH submitted 2020-11-30 cs.LG

classification cs.LG
keywords graphcyclesdatasetsfaillocalmodelnetworkssimple
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Despite quick progress in the last few years, recent studies have shown that modern graph neural networks can still fail at very simple tasks, like detecting small cycles. This hints at the fact that current networks fail to catch information about the local structure, which is problematic if the downstream task heavily relies on graph substructure analysis, as in the context of chemistry. We propose a very simple correction to the now standard GIN convolution that enables the network to detect small cycles with nearly no cost in terms of computation time and number of parameters. Tested on real life molecule property datasets, our model consistently improves performance on large multi-tasked datasets over all baselines, both globally and on a per-task setting.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. GNN Applied to Ego-nets for Friend Suggestions

    cs.SI 2024-12 conditional novelty 6.0 of 10

    WalkGNN, a pair-state graph neural network run on ego-nets, is reported to outperform baselines for VK friend suggestions offline and lift friend-request CTR by 12 percent online.

Pith tools