English
Related papers

Related papers: From Isolation to Entanglement: When Do Interpreta…

200 papers

Humans have a remarkable ability to disentangle complex sensory inputs (e.g., image, text) into simple factors of variation (e.g., shape, color) without much supervision. This ability has inspired many works that attempt to solve the…

Machine Learning · Computer Science 2024-12-25 Kartik Ahuja , Divyat Mahajan , Vasilis Syrgkanis , Ioannis Mitliagkas

Mechanistic interpretability aims to understand how models store representations by breaking down neural networks into interpretable units. However, the occurrence of polysemantic neurons, or neurons that respond to multiple unrelated…

Computer Vision and Pattern Recognition · Computer Science 2023-04-20 Laura O'Mahony , Vincent Andrearczyk , Henning Muller , Mara Graziani

The advancement of robots, particularly those functioning in complex human-centric environments, relies on control solutions that are driven by machine learning. Understanding how learning-based controllers make decisions is crucial since…

Machine Learning · Computer Science 2023-11-14 Tsun-Hsuan Wang , Wei Xiao , Tim Seyde , Ramin Hasani , Daniela Rus

Sparse auto-encoders (SAEs) have become a prevalent tool for interpreting language models' inner workings. However, it is unknown how tightly SAE features correspond to computationally important directions in the model. This work…

Machine Learning · Computer Science 2025-02-25 Thomas Dooms , Daniel Wilhelm

Improving controllability or the ability to manipulate one or more attributes of the generated data has become a topic of interest in the context of deep generative models of music. Recent attempts in this direction have relied on learning…

Sound · Computer Science 2021-08-04 Ashis Pati , Alexander Lerch

For machine learning models to be most useful in numerous sociotechnical systems, many have argued that they must be human-interpretable. However, despite increasing interest in interpretability, there remains no firm consensus on how to…

Machine Learning · Computer Science 2021-02-03 Andrew Slavin Ross , Nina Chen , Elisa Zhao Hang , Elena L. Glassman , Finale Doshi-Velez

Learning visual representations with interpretable features, i.e., disentangled representations, remains a challenging problem. Existing methods demonstrate some success but are hard to apply to large-scale vision datasets like ImageNet. In…

Machine Learning · Computer Science 2023-06-01 Lilian Ngweta , Subha Maity , Alex Gittens , Yuekai Sun , Mikhail Yurochkin

Recent years have seen growing interest in learning disentangled representations, in which distinct features, such as size or shape, are represented by distinct neurons. Quantifying the extent to which a given representation is disentangled…

Machine Learning · Computer Science 2023-04-06 Louis Mahon , Lei Shah , Thomas Lukasiewicz

Learning disentangled representations of real-world data is a challenging open problem. Most previous methods have focused on either supervised approaches which use attribute labels or unsupervised approaches that manipulate the…

Computation and Language · Computer Science 2021-01-26 Vikash Balasubramanian , Ivan Kobyzev , Hareesh Bahuleyan , Ilya Shapiro , Olga Vechtomova

Disentangled latent spaces usually have better semantic separability and geometrical properties, which leads to better interpretability and more controllable data generation. While this has been well investigated in Computer Vision, in…

Computation and Language · Computer Science 2024-06-12 Yingji Zhang , Danilo S. Carvalho , André Freitas

Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration to identify a canonical set of features is challenged by…

Machine Learning · Computer Science 2025-05-27 Xiangchen Song , Aashiq Muhamed , Yujia Zheng , Lingjing Kong , Zeyu Tang , Mona T. Diab , Virginia Smith , Kun Zhang

Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising…

Computation and Language · Computer Science 2026-02-27 Usha Bhalla , Alex Oesterling , Claudio Mayrink Verdun , Himabindu Lakkaraju , Flavio P. Calmon

Node representations, or embeddings, are low-dimensional vectors that capture node properties, typically learned through unsupervised structural similarity objectives or supervised tasks. While recent efforts have focused on explaining…

Machine Learning · Computer Science 2025-10-17 Simone Piaggesi , André Panisson , Megha Khosla

The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often not statistically independent. In this work, we bridge the…

Recently there has been a significant interest in learning disentangled representations, as they promise increased interpretability, generalization to unseen scenarios and faster learning on downstream tasks. In this paper, we investigate…

Machine Learning · Computer Science 2019-10-30 Francesco Locatello , Gabriele Abbati , Tom Rainforth , Stefan Bauer , Bernhard Schölkopf , Olivier Bachem

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Wei-Lun Chao , Tanya Berger-Wolf , Yu Su

Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted attention due to…

Machine Learning · Computer Science 2026-05-13 Hyeonjin Kim , Hangyeol Jung , Heechan Yun , Sungjun Yun , Dong-Jun Han

People's associations between colors and concepts influence their ability to interpret the meanings of colors in information visualizations. Previous work has suggested such effects are limited to concepts that have strong, specific…

Human-Computer Interaction · Computer Science 2023-09-22 Kushin Mukherjee , Brian Yin , Brianne E. Sherman , Laurent Lessard , Karen B. Schloss

Learning to disentangle and represent factors of variation in data is an important problem in AI. While many advances have been made to learn these representations, it is still unclear how to quantify disentanglement. While several metrics…

Machine Learning · Computer Science 2022-05-10 Marc-André Carbonneau , Julian Zaidi , Jonathan Boilard , Ghyslain Gagnon

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