English
Related papers

Related papers: Is Sparse Attention more Interpretable?

200 papers

While a lot of research in explainable AI focuses on producing effective explanations, less work is devoted to the question of how people understand and interpret the explanation. In this work, we focus on this question through a study of…

Computation and Language · Computer Science 2022-06-20 Hendrik Schuff , Alon Jacovi , Heike Adel , Yoav Goldberg , Ngoc Thang Vu

We consider the problem of visually explaining similarity models, i.e., explaining why a model predicts two images to be similar in addition to producing a scalar score. While much recent work in visual model interpretability has focused on…

Computer Vision and Pattern Recognition · Computer Science 2020-10-15 Meng Zheng , Srikrishna Karanam , Terrence Chen , Richard J. Radke , Ziyan Wu

Attention layers, as commonly used in transformers, form the backbone of modern deep learning, yet there is no mathematical description of their benefits and deficiencies as compared with other architectures. In this work we establish both…

Machine Learning · Computer Science 2023-11-17 Clayton Sanford , Daniel Hsu , Matus Telgarsky

We describe an "interpretability illusion" that arises when analyzing the BERT model. Activations of individual neurons in the network may spuriously appear to encode a single, simple concept, when in fact they are encoding something far…

Computation and Language · Computer Science 2021-04-16 Tolga Bolukbasi , Adam Pearce , Ann Yuan , Andy Coenen , Emily Reif , Fernanda Viégas , Martin Wattenberg

Regression with sparse inputs is a common theme for large scale models. Optimizing the underlying linear algebra for sparse inputs allows such models to be estimated faster. At the same time, centering the inputs has benefits in improving…

Computation · Statistics 2019-10-30 Jeffrey Wong

The attention mechanism is a core component of the Transformer architecture. Beyond improving performance, attention has been proposed as a mechanism for explainability via attention weights, which are associated with input features (e.g.,…

Computation and Language · Computer Science 2025-08-15 Andrés Carvallo , Denis Parra , Peter Brusilovsky , Hernan Valdivieso , Gabriel Rada , Ivania Donoso , Vladimir Araujo

Attention modules, as simple and effective tools, have not only enabled deep neural networks to achieve state-of-the-art results in many domains, but also enhanced their interpretability. Most current models use deterministic attention…

Machine Learning · Statistics 2020-10-22 Xinjie Fan , Shujian Zhang , Bo Chen , Mingyuan Zhou

Interpretability is a pressing issue for machine learning. Common approaches to interpretable machine learning constrain interactions between features of the input, rendering the effects of those features on a model's output comprehensible…

Machine Learning · Computer Science 2023-05-11 Kieran A. Murphy , Dani S. Bassett

Neural network architectures in natural language processing often use attention mechanisms to produce probability distributions over input token representations. Attention has empirically been demonstrated to improve performance in various…

Computation and Language · Computer Science 2021-05-10 George Chrysostomou , Nikolaos Aletras

As machine learning models are increasingly deployed in high-stakes domains, the need for interpretability has grown to meet strict regulatory and accountability constraints. Despite this interest, systematic evaluations of inherently…

Machine Learning · Computer Science 2026-03-27 Mattia Billa , Giovanni Orlandi , Veronica Guidetti , Federica Mandreoli

Transformer models have become the dominant backbone for sequence modeling, leveraging self-attention to produce contextualized token representations. These are typically aggregated into fixed-size vectors via pooling operations for…

Machine Learning · Computer Science 2025-10-07 Sofiane Ennadir , Levente Zólyomi , Oleg Smirnov , Tianze Wang , John Pertoft , Filip Cornell , Lele Cao

With the growing pervasiveness of artificial intelligence, the ability to explain the inferences made by machine learning models has become increasingly important. Numerous techniques for model explainability have been proposed, with…

Human-Computer Interaction · Computer Science 2026-04-08 Nicola Rossberg , Bennett Kleinberg , Barry O'Sullivan , Luca Longo , Andrea Visentin

Models based on the Transformer architecture have achieved better accuracy than the ones based on competing architectures for a large set of tasks. A unique feature of the Transformer is its universal application of a self-attention…

Machine Learning · Computer Science 2020-10-01 Nan Ding , Xinjie Fan , Zhenzhong Lan , Dale Schuurmans , Radu Soricut

Choice models, which capture popular preferences over objects of interest, play a key role in making decisions whose eventual outcome is impacted by human choice behavior. In most scenarios, the choice model, which can effectively be viewed…

Methodology · Statistics 2011-09-22 Vivek F. Farias , Srikanth Jagabathula , Devavrat Shah

Modern neural networks are often augmented with an attention mechanism, which tells the network where to focus within the input. We propose in this paper a new framework for sparse and structured attention, building upon a smoothed max…

Machine Learning · Statistics 2019-02-26 Vlad Niculae , Mathieu Blondel

The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability. Despite strong performance, these models are often treated as black boxes, with limited systematic investigation of their…

Machine Learning · Computer Science 2026-05-13 Konstantinos P. Panousis , Diego Marcos

Despite the fact that Transformers perform well in NLP tasks, recent studies suggest that self-attention is theoretically limited in learning even some regular and context-free languages. These findings motivated us to think about their…

Computation and Language · Computer Science 2023-10-20 Shunjie Wang , Shane Steinert-Threlkeld

Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in…

Computation and Language · Computer Science 2021-10-07 Biao Zhang , Ivan Titov , Rico Sennrich

Diverse and extensive work has recently been conducted on text-conditioned human motion generation. However, progress in the reverse direction, motion captioning, has seen less comparable advancement. In this paper, we introduce a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Karim Radouane , Julien Lagarde , Sylvie Ranwez , Andon Tchechmedjiev

Attention models have become a crucial component in neural machine translation (NMT). They are often implicitly or explicitly used to justify the model's decision in generating a specific token but it has not yet been rigorously established…

Computation and Language · Computer Science 2019-10-02 Pooya Moradi , Nishant Kambhatla , Anoop Sarkar
‹ Prev 1 4 5 6 7 8 10 Next ›