Pith. sign in

Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Multiple sampling-based methods have been developed for approximating and accelerating node embedding aggregation in graph convolutional networks (GCNs) training. Among them, a layer-wise approach recursively performs importance sampling to select neighbors jointly for existing nodes in each layer. This paper revisits the approach from a matrix approximation perspective, and identifies two issues in the existing layer-wise sampling methods: suboptimal sampling probabilities and estimation biases induced by sampling without replacement. To address these issues, we accordingly propose two remedies: a new principle for constructing sampling probabilities and an efficient debiasing algorithm. The improvements are demonstrated by extensive analyses of estimation variance and experiments on common benchmarks. Code and algorithm implementations are publicly available at https://github.com/ychen-stat-ml/GCN-layer-wise-sampling .

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

REJECT 1

roles

background 1

polarities

unclear 1

representative citing papers

DAFOS: Dynamic Adaptive Fanout Optimization Sampler

cs.LG · 2025-07-08 · reject · novelty 4.0

DAFOS trains GNNs faster by starting with small fanout, increasing it when loss plateaus, and prioritizing high-degree nodes, but its speedup claims are confounded by an unfair early stopping comparison.

citing papers explorer

Showing 1 of 1 citing paper.

  • DAFOS: Dynamic Adaptive Fanout Optimization Sampler cs.LG · 2025-07-08 · reject · none · ref 1 · internal anchor

    DAFOS trains GNNs faster by starting with small fanout, increasing it when loss plateaus, and prioritizing high-degree nodes, but its speedup claims are confounded by an unfair early stopping comparison.