跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2610.15020 · v2

PATTERN Can Be Solved from Memory: Testing Graph Neural Networks on Unseen Patterns

首次提交 2026-10-10 23:54
版本更新 2026-11-13 17:19
雷达观测 2026-11-16 11:42
arXiv ↗PDF ↗

摘要

PATTERN asks graph neural networks to find a planted subgraph in a new host graph. The hosts change, but the benchmark draws just 100 patterns and reuses them across training and test splits. A lookup that extracts these patterns from the training labels achieves 96.6% class-weighted accuracy on the official test split, above every published result, without fitting a model or consulting the generator. On unseen patterns, the same lookup scores 50.6%. A matcher that also uses the generator reaches 99.2% on the official split. Among five graph networks we retrained, GRASS and PPGT go from the top two on the official split to the bottom two on unseen patterns. Each loses 8.1 percentage points even when familiar and unseen patterns are matched in size. Logistic regression on two-hop node statistics scores above every run of the five networks on unseen patterns. For CKGConv, the advantage follows the training patterns: it reappears with each of three independently drawn pattern libraries and disappears when every training and validation graph gets a new pattern. Generator-based inference also scores 82.3% on CLUSTER, compared with a published best of 81.6%. On Minesweeper's released board, four of eight planned chains produced samples within the time budget; none converged, but their pooled predictions reached 99.86% ROC AUC, above the published best of 99.55%. PATTERN's official split tests its intended task of finding familiar patterns in new graphs. We recommend reporting the same checkpoint's score on unseen patterns alongside it.

作者备注:48 pages, 6 figures

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-13 17:19 · 最新观测版本

PATTERN Can Be Solved from Memory: Testing Graph Neural Networks on Unseen Patterns

PATTERN asks graph neural networks to find a planted subgraph in a new host graph. The hosts change, but the benchmark draws just 100 patterns and reuses them across training and test splits. A lookup that extracts these patterns from the training labels achieves 96.6% class-weighted accuracy on the official test split, above every published result, without fitting a model or consulting the generator. On unseen patterns, the same lookup scores 50.6%. A matcher that also uses the generator reaches 99.2% on the official split. Among five graph networks we retrained, GRASS and PPGT go from the top two on the official split to the bottom two on unseen patterns. Each loses 8.1 percentage points even when familiar and unseen patterns are matched in size. Logistic regression on two-hop node statistics scores above every run of the five networks on unseen patterns. For CKGConv, the advantage follows the training patterns: it reappears with each of three independently drawn pattern libraries and disappears when every training and validation graph gets a new pattern. Generator-based inference also scores 82.3% on CLUSTER, compared with a published best of 81.6%. On Minesweeper's released board, four of eight planned chains produced samples within the time budget; none converged, but their pooled predictions reached 99.86% ROC AUC, above the published best of 99.55%. PATTERN's official split tests its intended task of finding familiar patterns in new graphs. We recommend reporting the same checkpoint's score on unseen patterns alongside it.

查看此版本解读 →查看此版本原文 ↗