paper-with-me

홈 › Papers

Optimization and Interpretability of Graph Attention Networks for Small Sparse Graph Structures in Automotive Applications

2023-05-25 · Marion Neumeier, Andreas Tollkühn, Sebastian Dorn, Michael Botsch, Wolfgang Utschick

For automotive applications, the Graph Attention Network (GAT) is a prominently used architecture to include relational information of a traffic scenario during feature embedding. As shown in this work, however, one of the most popular GAT realizations, namely GATv2, has potential pitfalls that hinder an optimal parameter learning. Especially for small and sparse graph structures a proper optimization is problematic. To surpass limitations, this work proposes architectural modifications of GATv2. In controlled experiments, it is shown that the proposed model adaptions improve prediction performance in a node-level regression task and make it more robust to parameter initialization. This work aims for a better understanding of the attention mechanism and analyzes its interpretability of identifying causal importance.

📄 PDF Abstract BibTeX arXiv:2305.16196

Code (1)

MB-Team-THI/sparse-graph-attention-optimization 공식 구현 pytorch

Tasks

Graph Attention

Methods 이 논문이 사용한 방법론

GATv2 The __GATv2__ operator from the “How Attentive are Graph Attention Networks?” paper, which fixes the static attention problem of the standard…
GAT A Graph Attention Network (GAT) is a neural network architecture that operates on graph-structured data, leveraging masked self-attentional layers to address the shortcomings…

Similar Papers 제목 키워드 기반

Explainable Sparse Knowledge Graph Completion via High-order Graph Reasoning Network

2022-07-14 · Weijian Chen, Yixin Cao, Fuli Feng, Xiangnan He 외

Knowledge Graphs (KGs) are becoming increasingly essential infrastructures in many applications while suffering from incompleteness issues. The KG completion task (KGC) automatically predicts missing facts based on an in…

Knowledge Graph CompletionKnowledge GraphsVocal Bursts Intensity Prediction

HopFormer: Sparse Graph Transformers with Explicit Receptive Field Control

2026-02-02 · Sanggeon Yun, Raheeb Hassan, Ryozo Masukawa, Sungheon Jeong 외 arxiv

Graph Transformers typically rely on explicit positional or structural encodings and dense global attention to incorporate graph topology. In this work, we show that neither is essential. We introduce HopFormer, a graph …

Stream: Scaling up Mechanistic Interpretability to Long Context in LLMs via Sparse Attention

2025-10-22 · J Rosser, José Luis Redondo García, Gustavo Penha, Konstantina Palla 외 arxiv

As Large Language Models (LLMs) scale to million-token contexts, traditional Mechanistic Interpretability techniques for analyzing attention scale quadratically with context length, demanding terabytes of memory beyond 1…

Is Sparse Attention more Interpretable?

2021-06-02 · ACL 2021 5 · Clara Meister, Stefan Lazov, Isabelle Augenstein, Ryan Cotterell

Sparse attention has been claimed to increase model interpretability under the assumption that it highlights influential inputs. Yet the attention distribution is typically over representations internal to the model rath…

text-classificationText Classification

Mechanistic Interpretability for Transformer-based Time Series Classification

2025-11-26 · Matīss Kalnāre, Sofoklis Kitharidis, Thomas Bäck, Niki van Stein arxiv

Transformer-based models have become state-of-the-art tools in various machine learning tasks, including time series classification, yet their complexity makes understanding their internal decision-making challenging. Ex…

Time Series Classification