English
Related papers

Related papers: Interpretable Feature Interaction via Statistical …

200 papers

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…

Machine Learning · Computer Science 2023-10-05 Hoagy Cunningham , Aidan Ewart , Logan Riggs , Robert Huben , Lee Sharkey

Contemporary predictive models are hard to interpret as their deep nets exploit numerous complex relations between input elements. This work suggests a theoretical framework for model interpretability by measuring the contribution of…

Machine Learning · Computer Science 2022-06-15 Itai Gat , Nitay Calderon , Roi Reichart , Tamir Hazan

This work presents StrAE: a Structured Autoencoder framework that through strict adherence to explicit structure, and use of a novel contrastive objective over tree-structured representations, enables effective learning of multi-level…

Computation and Language · Computer Science 2025-02-25 Mattia Opper , Victor Prokhorov , N. Siddharth

Sparse Autoencoder (SAE) features have become essential tools for mechanistic interpretability research. SAE features are typically characterized by examining their activating examples, which are often "monosemantic" and align with human…

Artificial Intelligence · Computer Science 2025-09-30 Claire Tian , Katherine Tian , Nathan Hu

Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diffusion models.…

Machine Learning · Computer Science 2025-07-14 Stepan Shabalin , Ayush Panda , Dmitrii Kharlapenko , Abdur Raheem Ali , Yixiong Hao , Arthur Conmy

In this paper, we introduce Partial Information Decomposition of Features (PIDF), a new paradigm for simultaneous data interpretability and feature selection. Contrary to traditional methods that assign a single importance value, our…

Machine Learning · Computer Science 2025-11-17 Charles Westphal , Stephen Hailes , Mirco Musolesi

Spectroscopy is a central pillar of materials characterization, providing useful information on properties like structure, composition, or excited state dynamics of a system. However, many spectroscopic techniques present challenges in…

Materials Science · Physics 2026-04-09 Amalya C. Johnson , Chris Fajardo , Leena Sansguiri , Weike Ye , Steven B. Torrisi

Data-driven materials discovery requires large-scale experimental datasets, yet most of the information remains trapped in unstructured literature. Existing extraction efforts often focus on a limited set of features and have not addressed…

Computation and Language · Computer Science 2025-10-08 Xin Wang , Anshu Raj , Matthew Luebbe , Haiming Wen , Shuozhi Xu , Kun Lu

Sparse autoencoders (SAEs) have emerged as a powerful tool for uncovering interpretable features in large language models (LLMs) through the sparse directions they learn. However, the sheer number of extracted directions makes comprehensive…

Computation and Language · Computer Science 2025-11-11 Xinyuan Yan , Shusen Liu , Kowshik Thopalli , Bei Wang

Many-Objective Feature Selection (MOFS) approaches use four or more objectives to determine the relevance of a subset of features in a supervised learning task. As a consequence, MOFS typically returns a large set of non-dominated…

Machine Learning · Computer Science 2023-12-01 Uchechukwu F. Njoku , Alberto Abelló , Besim Bilalli , Gianluca Bontempi

Self-supervised learning has been shown to be very effective in learning useful representations, and yet much of the success is achieved in data types such as images, audio, and text. The success is mainly enabled by taking advantage of…

Machine Learning · Computer Science 2021-10-28 Talip Ucar , Ehsan Hajiramezanali , Lindsay Edwards

Part-level features are crucial for image understanding, but few studies focus on them because of the lack of fine-grained labels. Although unsupervised part discovery can eliminate the reliance on labels, most of them cannot maintain…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 Jiahao Xia , Yike Wu , Wenjian Huang , Jianguo Zhang , Jian Zhang

Understanding how features evolve across layers in deep neural networks is a fundamental challenge in mechanistic interpretability, particularly due to polysemanticity and feature superposition. While Sparse Autoencoders (SAEs) have been…

Machine Learning · Computer Science 2025-03-04 Nikita Balagansky , Ian Maksimov , Daniil Gavrilov

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

Jointly identifying a mixture of discrete and continuous factors of variability without supervision is a key problem in unraveling complex phenomena. Variational inference has emerged as a promising method to learn interpretable mixture…

Machine Learning · Computer Science 2021-04-14 Yeganeh M. Marghi , Rohan Gala , Uygar Sümbül

Interpretable machine learning has emerged as central in leveraging artificial intelligence within high-stakes domains such as healthcare, where understanding the rationale behind model predictions is as critical as achieving high…

Machine Learning · Computer Science 2024-04-30 Christel Sirocchi , Martin Urschler , Bastian Pfeifer

Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel…

Machine Learning · Computer Science 2025-02-20 Antoine Ledent , Peng Liu

Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…

Computation and Language · Computer Science 2023-06-27 Minxue Xia , Hao Zhu

Feature selection is an essential process in machine learning, especially when dealing with high-dimensional datasets. It helps reduce the complexity of machine learning models, improve performance, mitigate overfitting, and decrease…

Machine Learning · Computer Science 2024-10-10 Egor Kraev , Baran Koseoglu , Luca Traverso , Mohammed Topiwalla

Sparse autoencoders (SAEs) have emerged as a promising approach in language model interpretability, offering unsupervised extraction of sparse features. For interpretability methods to succeed, they must identify abstract features across…

Machine Learning · Computer Science 2025-09-08 Lovis Heindrich , Philip Torr , Fazl Barez , Veronika Thost
‹ Prev 1 4 5 6 7 8 10 Next ›