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.
Graph convolutions that can finally model local structure
1 Pith paper cite this work. Polarity classification is still indexing.
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.
citation-role summary
citation-polarity summary
fields
cs.SI 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
GNN Applied to Ego-nets for Friend Suggestions
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.