paper-with-me

홈 › Papers

Scaling Graph Transformers: A Comparative Study of Sparse and Dense Attention

2025-08-24 · Leon Dimitrov arxiv

Graphs have become a central representation in machine learning for capturing relational and structured data across various domains. Traditional graph neural networks often struggle to capture long-range dependencies between nodes due to their local structure. Graph transformers overcome this by using attention mechanisms that allow nodes to exchange information globally. However, there are two types of attention in graph transformers: dense and sparse. In this paper, we compare these two attention mechanisms, analyze their trade-offs, and highlight when to use each. We also outline current challenges and problems in designing attention for graph transformers.

📄 PDF Abstract BibTeX arXiv:2508.17175

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

What Structural Inductive Bias Helps Transformers Reason Over Knowledge Graphs? A Study with Tabula RASA

2026-02-02 · Jonas Petersen, Camilla Mazzoleni, Gian-Alessandro Lombardi, Federico Martelli 외 arxiv

What structural inductive bias helps transformers reason over knowledge graphs? Through controlled ablations of a minimal transformer modification with four independently removable components (sparse adjacency masking, e…

Knowledge Graphs

Sparse is Enough in Scaling Transformers

2021-11-24 · NeurIPS 2021 12 · Sebastian Jaszczur, Aakanksha Chowdhery, Afroz Mohiuddin, Łukasz Kaiser 외

Large Transformer models yield impressive results on many tasks, but are expensive to train, or even fine-tune, and so slow at decoding that their use and study becomes out of reach. We address this problem by leveraging…

Text Summarization

A Comparative Study on Dynamic Graph Embedding based on Mamba and Transformers

2024-12-15 · Ashish Parmanand Pandey, Alan John Varghese, Sarang Patil, Mengjia Xu

Dynamic graph embedding has emerged as an important technique for modeling complex time-evolving networks across diverse domains. While transformer-based models have shown promise in capturing long-range dependencies in …

Computational EfficiencyDynamic graph embeddingGraph EmbeddingGraph Representation Learning+4

xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity

2025-10-02 · Maximilian Beck, Kajetan Schweighofer, Sebastian Böck, Sebastian Lehner 외 arxiv

Scaling laws play a central role in the success of Large Language Models (LLMs), enabling the prediction of model performance relative to compute budgets prior to training. While Transformers have been the dominant archi…

Even Sparser Graph Transformers

2024-11-25 · Hamed Shirzad, Honghao Lin, Balaji Venkatachalam, Ameya Velingker 외

Graph Transformers excel in long-range dependency modeling, but generally require quadratic memory complexity in the number of nodes in an input graph, and hence have trouble scaling to large graphs. Sparse attention var…