Pith. sign in

arXiv preprint arXiv:2007.12374 , year=

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

RADE: Random Add-Drop Edge as a Regularizer

cs.LG · 2026-05-30 · unverdicted · novelty 6.0

Random Add-Drop Edge (RADE) jointly drops and adds edges stochastically during GNN training, with provable train-inference alignment and an adaptive rate balancer, to regularize against overfitting and mitigate over-squashing.

citing papers explorer

Showing 2 of 2 citing papers.

  • Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation cs.LG · 2026-06-21 · unverdicted · none · ref 35

    GaRA generates task-specific LoRA weight updates conditioned on graph structures to enable better whole-graph encoding in LLMs for zero-shot graph learning.

  • RADE: Random Add-Drop Edge as a Regularizer cs.LG · 2026-05-30 · unverdicted · none · ref 13

    Random Add-Drop Edge (RADE) jointly drops and adds edges stochastically during GNN training, with provable train-inference alignment and an adaptive rate balancer, to regularize against overfitting and mitigate over-squashing.