English
Related papers

Related papers: A Probabilistic Interpretation of Transformers

200 papers

We highlight a perhaps important but hitherto unobserved insight: The attention module in a transformer is a smoothed cubic spline. Viewed in this manner, this mysterious but critical component of a transformer becomes a natural development…

Artificial Intelligence · Computer Science 2024-08-20 Zehua Lai , Lek-Heng Lim , Yucong Liu

Operator learning enables data-driven modeling of partial differential equations (PDEs) by learning mappings between function spaces. However, scaling transformer-based operator models to high-resolution, multiscale domains remains a…

Machine Learning · Computer Science 2025-06-11 Arthur Feeney , Kuei-Hsiang Huang , Aparna Chandramowlishwaran

Attention mechanism is contributing to the majority of recent advances in machine learning for natural language processing. Additionally, it results in an attention map that shows the proportional influence of each input in its decision.…

Computation and Language · Computer Science 2025-01-23 Duc Hau Nguyen , Cyrielle Mallart , Guillaume Gravier , Pascale Sébillot

Large language models have been successful at tasks involving basic forms of in-context reasoning, such as generating coherent language, as well as storing vast amounts of knowledge. At the core of the Transformer architecture behind such…

Machine Learning · Computer Science 2025-03-10 Lei Chen , Joan Bruna , Alberto Bietti

Interpreting the inner workings of neural models is a key step in ensuring the robustness and trustworthiness of the models, but work on neural network interpretability typically faces a trade-off: either the models are too constrained to…

Computation and Language · Computer Science 2020-11-11 Phong Le , Willem Zuidema

Transformers have emerged as a widely used neural network model for various natural language processing tasks. Previous research explored their relationship with constant-depth threshold circuits, making two assumptions: average-hard…

Computation and Language · Computer Science 2023-08-23 Lena Strobl

Attention networks such as transformers have achieved state-of-the-art performance in many domains. These networks rely heavily on the dot product attention operator, which computes the similarity between two points by taking their inner…

Machine Learning · Computer Science 2023-12-05 Albert Tseng , Tao Yu , Toni J. B. Liu , Christopher De Sa

In this work we propose an energy functional along the lines of Modern Hopfield Networks (MNH), the stationary points of which correspond to the attention due to Vaswani et al. [12], thus unifying both frameworks. The minima of this…

Machine Learning · Statistics 2025-06-16 Ahmed Farooq

In the paper we show that there is an analogy between the operations occurring in a layer of a transformer (projections and layer normalizations, disregarding the feedforward neural network) and a step in the power method. Coherently with…

Machine Learning · Computer Science 2026-05-26 Chenglong Li , Claudio Altafini

Many visual scenes can be described as compositions of latent factors. Effective recognition, reasoning, and editing often require not only forming such compositional representations, but also solving the decomposition problem. One popular…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Calvin Yeung , Ali Zakeri , Zhuowen Zou , Mohsen Imani

The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the…

Computation and Language · Computer Science 2019-06-20 Jesse Vig , Yonatan Belinkov

Transformers, adapted from natural language processing, are emerging as a leading approach for graph representation learning. Contemporary graph transformers often treat nodes or edges as separate tokens. This approach leads to…

Machine Learning · Computer Science 2023-10-04 Zihan Pengmei , Zimu Li , Chih-chan Tien , Risi Kondor , Aaron R. Dinner

The incredible success of transformers on sequence modeling tasks can be largely attributed to the self-attention mechanism, which allows information to be transferred between different parts of a sequence. Self-attention allows…

Machine Learning · Computer Science 2024-08-14 Eshaan Nichani , Alex Damian , Jason D. Lee

Deep learning models for tabular data typically do not allow for imposing a graph of external dependencies between samples, which can be useful for accounting for relatedness in tasks such as treatment effect estimation. Graph neural…

Machine Learning · Computer Science 2025-12-09 Andrei V. Konstantinov , Valerii A. Zuev , Lev V. Utkin

Prior-data fitted networks (PFNs) have recently emerged as a powerful approach for Bayesian prediction tasks, approximating the posterior predictive distribution (PPD) through in-context learning. Despite their strong empirical performance…

Machine Learning · Statistics 2026-05-27 Gyeonghun Kang , Changwoo J. Lee , Xiang Cheng

Standard attention-based transformers are known to exhibit instability under learning rate overspecification during training, particularly at high learning rates. While various methods have been proposed to improve resilience to such…

Machine Learning · Computer Science 2026-02-02 Shyam Venkatasubramanian , Sean Moushegian , Michael Lin , Mir Park , Ankit Singhal , Connor Lee

This paper is a contribution towards interpretability of the deep learning models in different applications of time-series. We propose a temporal attention layer that is capable of selecting the relevant information to perform various…

Computer Vision and Pattern Recognition · Computer Science 2018-06-25 Phongtharin Vinayavekhin , Subhajit Chaudhury , Asim Munawar , Don Joven Agravante , Giovanni De Magistris , Daiki Kimura , Ryuki Tachibana

We propose a new framework for binary classification in transfer learning settings where both covariate and label distributions may shift between source and target domains. Unlike traditional covariate shift or label shift assumptions, we…

Methodology · Statistics 2025-09-29 Manli Cheng , Subha Maity , Qinglong Tian , Pengfei Li

Neural networks are growing more capable on their own, but we do not understand their neural mechanisms. Understanding these mechanisms' decision-making processes, or mechanistic interpretability, enables (1) accountability and control in…

Computation and Language · Computer Science 2026-03-02 Mason Kadem , Rong Zheng

We propose and analyze a new variation of the so-called {\em exponential Hopfield model}, a recently introduced family of associative neural networks with unprecedented storage capacity. Our construction is based on a cost function defined…

Disordered Systems and Neural Networks · Physics 2025-09-09 Linda Albanese , Andrea Alessandrelli , Adriano Barra , Peter Sollich