English
Related papers

Related papers: Routing Absorption in Sparse Attention: Why Random…

200 papers

Attention mechanisms in deep learning architectures have often been used as a means of transparency and, as such, to shed light on the inner workings of the architectures. Recently, there has been a growing interest in whether or not this…

Computation and Language · Computer Science 2019-11-12 Joris Baan , Maartje ter Hoeve , Marlies van der Wees , Anne Schuth , Maarten de Rijke

Existing approaches to increasing the effective depth of Transformers predominantly rely on parameter reuse, extending computation through recursive execution. Under this paradigm, the network structure remains static along the training…

Computation and Language · Computer Science 2026-04-17 Yao Chen , Yilong Chen , Yinqi Yang , Junyuan Shang , Zhenyu Zhang , Zefeng Zhang , Shuaiyi Nie , Shuohuan Wang , Yu Sun , Hua Wu , HaiFeng Wang , Tingwen Liu

Top-K sparse softmax gating mixture of experts has been widely used for scaling up massive deep-learning architectures without increasing the computational cost. Despite its popularity in real-world applications, the theoretical…

Machine Learning · Statistics 2024-02-27 Huy Nguyen , Pedram Akbarian , Fanqi Yan , Nhat Ho

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, edge-type biases,…

Machine Learning · Computer Science 2026-05-12 Jonas Petersen , Camilla Mazzoleni , Gian-Alessandro Lombardi , Federico Martelli , Riccardo Maggioni

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 variants such as…

Machine Learning · Computer Science 2024-11-26 Hamed Shirzad , Honghao Lin , Balaji Venkatachalam , Ameya Velingker , David Woodruff , Danica Sutherland

Attention mechanisms that confer selective focus on a strict subset of input elements are nearly ubiquitous in language models today. We posit there to be downside to the use of attention: most input information is lost. In support of this…

Computation and Language · Computer Science 2025-03-21 Benjamin L. Badger

Learning algorithms become more powerful, often at the cost of increased complexity. In response, the demand for algorithms to be transparent is growing. In NLP tasks, attention distributions learned by attention-based deep learning models…

Computation and Language · Computer Science 2019-07-09 Joris Baan , Maartje ter Hoeve , Marlies van der Wees , Anne Schuth , Maarten de Rijke

Sparse Mixture of Experts (SMoE) has emerged as a key to achieving unprecedented scalability in deep learning. By activating only a small subset of parameters per sample, SMoE achieves an exponential increase in parameter counts while…

Machine Learning · Computer Science 2025-05-05 Tam Nguyen , Ngoc N. Tran , Khai Nguyen , Richard G. Baraniuk

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 rather than the inputs…

Computation and Language · Computer Science 2021-06-09 Clara Meister , Stefan Lazov , Isabelle Augenstein , Ryan Cotterell

One of the limitations of transformer networks is the sequence length due to the quadratic nature of the attention matrix. Classical self attention uses the entire sequence length, however, the actual attention being used is sparse. Humans…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Marc Estafanous

Recent advances in efficient Transformers have exploited either the sparsity or low-rank properties of attention matrices to reduce the computational and memory bottlenecks of modeling long sequences. However, it is still challenging to…

Machine Learning · Computer Science 2021-10-29 Beidi Chen , Tri Dao , Eric Winsor , Zhao Song , Atri Rudra , Christopher Ré

Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces. Concerning the information aggregation, a common practice is to use a concatenation followed by a…

Computation and Language · Computer Science 2019-04-08 Jian Li , Baosong Yang , Zi-Yi Dou , Xing Wang , Michael R. Lyu , Zhaopeng Tu

Sparse Mixture-of-Experts (SMoE) models enable scaling language models efficiently, but training them remains challenging, as routing can collapse onto few experts and auxiliary load-balancing losses can reduce specialization. Motivated by…

Machine Learning · Computer Science 2026-05-13 Sagi Ahrac , Noya Hochwald , Mor Geva

Transformer has achieved great success in NLP. However, the quadratic complexity of the self-attention mechanism in Transformer makes it inefficient in handling long sequences. Many existing works explore to accelerate Transformers by…

Computation and Language · Computer Science 2021-09-03 Chuhan Wu , Fangzhao Wu , Tao Qi , Binxing Jiao , Daxin Jiang , Yongfeng Huang , Xing Xie

While Transformer architecture excel at modeling long-range dependencies contributing to its widespread adoption in vision tasks the quadratic complexity of softmax-based attention mechanisms imposes a major bottleneck, particularly when…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yuan Cao , Dong Wang

The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently. In one vein of study, researchers are interested in understanding why and how transformers work. In another vein, researchers…

Computation and Language · Computer Science 2022-10-28 Raymond Li , Wen Xiao , Linzi Xing , Lanjun Wang , Gabriel Murray , Giuseppe Carenini

The core challenge with continual learning is catastrophic forgetting, the phenomenon that when neural networks are trained on a sequence of tasks they rapidly forget previously learned tasks. It has been observed that catastrophic…

Machine Learning · Computer Science 2020-09-10 Mark Collier , Efi Kokiopoulou , Andrea Gesmundo , Jesse Berent

Real-world problems often involve complex and unstructured sets of measurements, which occur when sensors are sparsely placed in either space or time. Being able to model this irregular spatiotemporal data and extract meaningful forecasts…

Machine Learning · Computer Science 2024-04-17 Arnaud Pannatier , Kyle Matoba , François Fleuret

Transformer-based models have achieved state-of-the-art performance in jet tagging at the CERN Large Hadron Collider (LHC), with the Particle Transformer (ParT) representing a leading example of such models. A striking feature of ParT is…

In the physical design of integrated circuits, global and detailed routing are critical stages involving the determination of the interconnected paths of each net on a circuit while satisfying the design constraints. Existing actual routers…

Machine Learning · Computer Science 2020-06-01 Haiguang Liao , Qingyi Dong , Xuliang Dong , Wentai Zhang , Wangyang Zhang , Weiyi Qi , Elias Fallon , Levent Burak Kara