paper-with-me

Papers

Probing Graph Neural Network Activation Patterns Through Graph Topology

2026-02-24 · Floriano Tori, Lorenzo Bini, Marco Sorbi, Stéphane Marchand-Maillet, Vincent Ginis arxiv

Curvature notions on graphs provide a theoretical description of graph topology, highlighting bottlenecks and denser connected regions. Artifacts of the message passing paradigm in Graph Neural Networks, such as oversmoothing and oversquashing, have been attributed to these regions. However, it remains unclear how the topology of a graph interacts with the learned preferences of GNNs. Through Massive Activations, which correspond to extreme edge activation values in Graph Transformers, we probe this correspondence. Our findings on synthetic graphs and molecular benchmarks reveal that MAs do not preferentially concentrate on curvature extremes, despite their theoretical link to information flow. On the Long Range Graph Benchmark, we identify a systemic \textit{curvature shift}: global attention mechanisms exacerbate topological bottlenecks, drastically increasing the prevalence of negative curvature. Our work reframes curvature as a diagnostic probe for understanding when and why graph learning fails.

📄 PDF Abstract BibTeX arXiv:2602.21092

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Neural NetworkGraph Learning

Similar Papers 제목 키워드 기반

Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models

2025-09-22 · Katharina Simbeck, Mariam Mahran arxiv

Despite growing research on bias in large language models (LLMs), most work has focused on gender and race, with little attention to religious identity. This paper explores how religion is internally represented in LLMs …

Probing Neural Topology of Large Language Models

2025-06-01 · Yu Zheng, Yuan Yuan, Yong Li, Paolo Santi

Probing large language models (LLMs) has yielded valuable insights into their internal mechanisms by linking neural representations to interpretable semantics. However, how neurons functionally co-activate with each othe…

Functional ConnectivityGraph MatchingText Generation

Structural Graph Probing of Vision-Language Models

2026-03-28 · Haoyu He, Yue Zhuo, Yu Zheng, Qi R. Wang arxiv

Vision-language models (VLMs) achieve strong multimodal performance, yet how computation is organized across populations of neurons remains poorly understood. In this work, we study VLMs through the lens of neural topolo…

Demographic Prompting at Scale: When More Attributes Hurt LLM--Human Agreement

2026-07-12 · Mahammed Kamruzzaman, Shrabon Kumar Das, Gene Louis Kim arxiv

We investigate how annotator demographic attributes, supplied as prompt cues, shape the alignment between large language model (LLM) predictions and human annotations across five tasks. Using five open-source LLMs, we sy…

Interpreting CNN Knowledge via an Explanatory Graph

2017-08-05 · Quanshi Zhang, Ruiming Cao, Feng Shi, Ying Nian Wu 외

This paper learns a graphical model, namely an explanatory graph, which reveals the knowledge hierarchy hidden inside a pre-trained CNN. Considering that each filter in a conv-layer of a pre-trained CNN usually represent…

Object