paper-with-me

홈 › Papers

Linear Transformer Topological Masking with Graph Random Features

2024-10-04 · Isaac Reid, Kumar Avinava Dubey, Deepali Jain, Will Whitney, Amr Ahmed, Joshua Ainslie, Alex Bewley, Mithun Jacob, Aranyak Mehta, David Rendleman, Connor Schenck, Richard E. Turner, René Wagner, Adrian Weller, Krzysztof Choromanski

When training transformers on graph-structured data, incorporating information about the underlying topology is crucial for good performance. Topological masking, a type of relative position encoding, achieves this by upweighting or downweighting attention depending on the relationship between the query and keys in a graph. In this paper, we propose to parameterise topological masks as a learnable function of a weighted adjacency matrix -- a novel, flexible approach which incorporates a strong structural inductive bias. By approximating this mask with graph random features (for which we prove the first known concentration bounds), we show how this can be made fully compatible with linear attention, preserving $\mathcal{O}(N)$ time and space complexity with respect to the number of input tokens. The fastest previous alternative was $\mathcal{O}(N \log N)$ and only suitable for specific graphs. Our efficient masking algorithms provide strong performance gains for tasks on image and point cloud data, including with $>30$k nodes.

📄 PDF Abstract BibTeX arXiv:2410.03462

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive Bias

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers

2021-07-16 · Krzysztof Choromanski, Han Lin, Haoxian Chen, Tianyi Zhang 외

In this paper we provide, to the best of our knowledge, the first comprehensive approach for incorporating various masking mechanisms into Transformers architectures in a scalable way. We show that recent results on line…

Graph Attention

Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers

2024-06-22 · Krzysztof Choromanski, Arijit Sehanobish, Somnath Basu Roy Chowdhury, Han Lin 외

We present a new class of fast polylog-linear algorithms based on the theory of structured matrices (in particular low displacement rank) for integrating tensor fields defined on weighted trees. Several applications of t…

Graph Classification

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

On the Trainability of Masked Diffusion Language Models via Blockwise Locality

2026-04-27 · Yuxiang Wang, Yu Xiang, Baojian Zhou, Qifang Zhao 외 arxiv

Masked diffusion language models (MDMs) have recently emerged as a promising alternative to standard autoregressive large language models (AR-LLMs), yet their optimization can be substantially less stable. We study block…

What to Hide from Your Students: Attention-Guided Masked Image Modeling

2022-03-23 · Ioannis Kakogeorgiou, Spyros Gidaris, Bill Psomas, Yannis Avrithis 외

Transformers and masked language modeling are quickly being adopted and explored in computer vision as vision transformers and masked image modeling (MIM). In this work, we argue that image token masking differs from tok…

Language ModelingLanguage ModellingMasked Language ModelingSelf-Supervised Learning