English
Related papers

Related papers: Identifying Intervenable and Interpretable Feature…

200 papers

Learning discriminative powerful representations is a crucial step for machine learning systems. Introducing invariance against arbitrary nuisance or sensitive attributes while performing well on specific tasks is an important problem in…

Computer Vision and Pattern Recognition · Computer Science 2020-07-07 Mhd Hasan Sarhan , Nassir Navab , Abouzar Eslami , Shadi Albarqouni

Retrieval systems rely on representations learned by increasingly powerful models. However, due to the high training cost and inconsistencies in learned representations, there is significant interest in facilitating communication between…

Machine Learning · Computer Science 2026-05-20 Simone Ricci , Niccolò Biondi , Federico Pernici , Ioannis Patras , Alberto Del Bimbo

The ability to learn disentangled representations that split underlying sources of variation in high dimensional, unstructured data is important for data efficient and robust use of neural networks. While various approaches aiming towards…

Machine Learning · Statistics 2019-05-15 Raphael Suter , Đorđe Miladinović , Bernhard Schölkopf , Stefan Bauer

This work introduces a novel principle for disentanglement we call mechanism sparsity regularization, which applies when the latent factors of interest depend sparsely on observed auxiliary variables and/or past latent factors. We propose a…

Learning a causal directed acyclic graph from data is a challenging task that involves solving a combinatorial problem for which the solution is not always identifiable. A new line of work reformulates this problem as a continuous…

Machine Learning · Computer Science 2020-11-05 Philippe Brouillard , Sébastien Lachapelle , Alexandre Lacoste , Simon Lacoste-Julien , Alexandre Drouin

We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain…

Machine Learning · Computer Science 2026-05-19 George Ma , Zhongyuan Liang , Irene Y. Chen , Somayeh Sojoudi

Capturing contextual dependencies has proven useful to improve the representational power of deep neural networks. Recent approaches that focus on modeling global context, such as self-attention and non-local operation, achieve this goal by…

Computer Vision and Pattern Recognition · Computer Science 2021-06-15 Shenao Zhang , Li Shen , Zhifeng Li , Wei Liu

Mechanistic interpretability seeks to understand the internal mechanisms of machine learning models, where localization -- identifying the important model components -- is a key step. Activation patching, also known as causal tracing or…

Machine Learning · Computer Science 2024-01-18 Fred Zhang , Neel Nanda

Orthogonally invariant functions of symmetric matrices often inherit properties from their diagonal restrictions: von Neumann's theorem on matrix norms is an early example. We discuss the example of "identifiability", a common property of…

Optimization and Control · Mathematics 2013-04-15 Aris Daniilidis , Dmitriy Drusvyatskiy , Adrian S. Lewis

Sparse dictionary learning has been a rapidly growing technique in mechanistic interpretability to attack superposition and extract more human-understandable features from model activations. We ask a further question based on the extracted…

Machine Learning · Computer Science 2024-02-20 Zhengfu He , Xuyang Ge , Qiong Tang , Tianxiang Sun , Qinyuan Cheng , Xipeng Qiu

In designing generative models, it is commonly believed that in order to learn useful latent structure, we face a fundamental tension between expressivity and structure. In this paper we challenge this view by proposing a new approach to…

Machine Learning · Statistics 2026-04-03 Alex Markham , Isaac Hirsch , Jeri A. Chang , Liam Solus , Bryon Aragam

A major challenge in causal discovery from observational data is the absence of perfect interventions, making it difficult to distinguish causal features from spurious ones. We propose an innovative approach, Feature Matching Intervention…

Machine Learning · Statistics 2025-03-06 Haoze Li , Jun Xie

The use of machine learning (ML) in high-stakes societal decisions has encouraged the consideration of fairness throughout the ML lifecycle. Although data integration is one of the primary steps to generate high quality training data, most…

Machine Learning · Computer Science 2022-04-01 Sainyam Galhotra , Karthikeyan Shanmugam , Prasanna Sattigeri , Kush R. Varshney

Previous research on word embeddings has shown that sparse representations, which can be either learned on top of existing dense embeddings or obtained through model constraints during training time, have the benefit of increased…

Computation and Language · Computer Science 2018-09-26 Valentin Trifonov , Octavian-Eugen Ganea , Anna Potapenko , Thomas Hofmann

Despite unconditional feature inversion being the foundation of many image synthesis applications, training an inverter demands a high computational budget, large decoding capacity and imposing conditions such as autoregressive priors. To…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Renan A. Rojas-Gomez , Raymond A. Yeh , Minh N. Do , Anh Nguyen

To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…

Machine Learning · Computer Science 2022-02-24 Jayneel Parekh , Pavlo Mozharovskyi , Florence d'Alché-Buc

We aim to create the highest possible quality of treatment-control matches for categorical data in the potential outcomes framework. Matching methods are heavily used in the social sciences due to their interpretability, but most matching…

Machine Learning · Statistics 2019-06-11 Yameng Liu , Aw Dieng , Sudeepa Roy , Cynthia Rudin , Alexander Volfovsky

Machine learning transparency calls for interpretable explanations of how inputs relate to predictions. Feature attribution is a way to analyze the impact of features on predictions. Feature interactions are the contextual dependence…

Machine Learning · Statistics 2020-06-22 Michael Tsang , Sirisha Rambhatla , Yan Liu

Orthogonality regularization has been developed to prevent deep CNNs from training instability and feature redundancy. Among existing proposals, kernel orthogonality regularization enforces orthogonality by minimizing the residual between…

Computer Vision and Pattern Recognition · Computer Science 2023-06-19 Changhao Wu , Shenan Zhang , Fangsong Long , Ziliang Yin , Tuo Leng

Identifying causal parameters from observational data is fraught with subtleties due to the issues of selection bias and confounding. In addition, more complex questions of interest, such as effects of treatment on the treated and mediated…

Methodology · Statistics 2015-11-17 Ilya Shpitser , Eric Tchetgen Tchetgen