paper-with-me

Papers

Towards Invariance to Node Identifiers in Graph Neural Networks

2025-02-19 · Maya Bechler-Speicher, Moshe Eliasof, Carola-Bibiane Schonlieb, Ran Gilad-Bachrach, Amir Globerson

Message-Passing Graph Neural Networks (GNNs) are known to have limited expressive power, due to their message passing structure. One mechanism for circumventing this limitation is to add unique node identifiers (IDs), which break the symmetries that underlie the expressivity limitation. In this work, we highlight a key limitation of the ID framework, and propose an approach for addressing it. We begin by observing that the final output of the GNN should clearly not depend on the specific IDs used. We then show that in practice this does not hold, and thus the learned network does not possess this desired structural property. Such invariance to node IDs may be enforced in several ways, and we discuss their theoretical properties. We then propose a novel regularization method that effectively enforces ID invariance to the network. Extensive evaluations on both real-world and synthetic tasks demonstrate that our approach significantly improves ID invariance and, in turn, often boosts generalization performance.

📄 PDF Abstract BibTeX arXiv:2502.13660

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

How Expressive Are Graph Neural Networks in the Presence of Node Identifiers?

2026-01-29 · Arie Soeteman, Michael Benedikt, Martin Grohe, Balder ten Cate arxiv

Graph neural networks (GNNs) are a widely used class of machine learning models for graph-structured data, based on local aggregation over neighbors. GNNs have close connections to logic. In particular, their expressive …

Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning

2024-05-26 · Yuankai Luo, Hongkang Li, Qijiong Liu, Lei Shi 외

We present a novel end-to-end framework that generates highly compact (typically 6-15 dimensions), discrete (int4 type), and interpretable node representations, termed node identifiers (node IDs), to tackle inference cha…

Computational EfficiencyGraph ClassificationGraph ClusteringGraph Learning+4

GRAIN: Bridging Name and Narrative Shifts in Real-World Graph Reasoning through Invariance-Rewarded Agentic RL

2026-08-27 · Zike Yuan, Han Zhang, Jianzhi Yan, Le Liu 외 arxiv

Despite their potential in standardized graph tasks, Large Language Models (LLMs) remain brittle to real-world shifts in node identifiers and task formulation. While deterministic graph tools are invariant to such shifts…

Reinforcement LearningSemantic Parsing

ScaleNet: Scale Invariance Learning in Directed Graphs

2024-11-13 · Qin Jiang, Chengjia Wang, Michael Lones, Yingfang Yuan 외

Graph Neural Networks (GNNs) have advanced relational data analysis but lack invariance learning techniques common in image classification. In node classification with GNNs, it is actually the ego-graph of the center nod…

ClassificationGraph Learningimage-classificationImage Classification+1

On the Universality of Graph Neural Networks on Large Random Graphs

2021-05-27 · NeurIPS 2021 12 · Nicolas Keriven, Alberto Bietti, Samuel Vaiter

We study the approximation power of Graph Neural Networks (GNNs) on latent position random graphs. In the large graph limit, GNNs are known to converge to certain "continuous" models known as c-GNNs, which directly enabl…

Stochastic Block Model