English
Related papers

Related papers: Improving Robustness In Sparse Autoencoders via Ma…

200 papers

Sparse autoencoders provide a promising unsupervised approach for extracting interpretable features from a language model by reconstructing activations from a sparse bottleneck layer. Since language models learn many concepts, autoencoders…

Machine Learning · Computer Science 2024-06-07 Leo Gao , Tom Dupré la Tour , Henk Tillman , Gabriel Goh , Rajan Troll , Alec Radford , Ilya Sutskever , Jan Leike , Jeffrey Wu

Sparse Autoencoders (SAEs) have emerged as a powerful paradigm for disentangling feature superposition in transformer-based architectures, enabling precise control via activation steering. However, the theoretical foundations of…

Machine Learning · Computer Science 2026-05-08 Yunpeng Zhou

Sparse neural networks are a key factor in developing resource-efficient machine learning applications. We propose the novel and powerful sparse learning method Adaptive Regularized Training (ART) to compress dense into sparse networks.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Patrick Glandorf , Timo Kaiser , Bodo Rosenhahn

This work presents a new method for enhancing communication efficiency in stochastic Federated Learning that trains over-parameterized random networks. In this setting, a binary mask is optimized instead of the model weights, which are kept…

Machine Learning · Computer Science 2024-03-01 Mohamad Mestoukirdi , Omid Esrafilian , David Gesbert , Qianrui Li , Nicolas Gresset

Deep neural networks often suffer from poor generalization caused by complex and non-convex loss landscapes. One of the popular solutions is Sharpness-Aware Minimization (SAM), which smooths the loss landscape via minimizing the maximized…

Machine Learning · Computer Science 2022-10-25 Peng Mi , Li Shen , Tianhe Ren , Yiyi Zhou , Xiaoshuai Sun , Rongrong Ji , Dacheng Tao

We introduce sparse autoencoder neural operators (SAE-NOs), a new class of sparse autoencoders that operate in function spaces rather than fixed-dimensional Euclidean representations. We formalize the functional representation hypothesis,…

Machine Learning · Computer Science 2026-05-11 Bahareh Tolooshams , Ailsa Shen , Anima Anandkumar

Intermediate layers of large language models (LLMs) best predict human brain responses to language, one of the most robust findings in computational neurolinguistics, yet why remains mechanistically unexplained. We address this gap by…

Computation and Language · Computer Science 2026-05-25 Dongxin Guo , Jikun Wu , Siu Ming Yiu

Autoencoders have been widely used for dimensional reduction and feature extraction. Various types of autoencoders have been proposed by introducing regularization terms. Most of these regularizations improve representation learning by…

Machine Learning · Computer Science 2020-06-26 Yuzhu Guo , Kang Pan , Simeng Li , Zongchang Han , Kexin Wang , Li Li

Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM)…

Computation and Language · Computer Science 2025-02-04 Daniel Pluth , Yu Zhou , Vijay K. Gurbani

Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing unlearning strategies, ranging from gradient-based…

Computation and Language · Computer Science 2025-06-02 Xu Wang , Zihao Li , Benyou Wang , Yan Hu , Difan Zou

We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. Here, regularized autoencoders provide a popular approach by learning the identity mapping on the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-14 Alexander Bauer , Shinichi Nakajima , Klaus-Robert Müller

Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts perform the mask-then-reconstruct operation in the raw data…

Machine Learning · Computer Science 2023-04-07 Wenxuan Tu , Qing Liao , Sihang Zhou , Xin Peng , Chuan Ma , Zhe Liu , Xinwang Liu , Zhiping Cai

Sparse autoencoders (SAEs) aim to disentangle model activations into monosemantic, human-interpretable features. In practice, learned features are often redundant and vary across training runs and sparsity levels, which makes…

Machine Learning · Computer Science 2026-01-01 Cristina P. Martin-Linares , Jonathan P. Ling

Sparse dictionary learning (and, in particular, sparse autoencoders) attempts to learn a set of human-understandable concepts that can explain variation on an abstract space. A basic limitation of this approach is that it neither exploits…

Computation and Language · Computer Science 2025-06-03 Mark Muchane , Sean Richardson , Kiho Park , Victor Veitch

Sparse autoencoders (SAEs) are a promising approach to interpreting the internal representations of transformer language models. However, SAEs are usually trained separately on each transformer layer, making it difficult to use them to…

Machine Learning · Computer Science 2025-02-25 Tim Lawson , Lucy Farnik , Conor Houghton , Laurence Aitchison

Domain generalization aims to improve the generalization capability of machine learning systems to out-of-distribution (OOD) data. Existing domain generalization techniques embark upon stationary and discrete environments to tackle the…

Machine Learning · Computer Science 2022-06-17 Tiexin Qin , Shiqi Wang , Haoliang Li

The Universality Hypothesis in large language models (LLMs) claims that different models converge towards similar concept representations in their latent spaces. Providing evidence for this hypothesis would enable researchers to exploit…

Machine Learning · Computer Science 2025-05-22 Michael Lan , Philip Torr , Austin Meek , Ashkan Khakzar , David Krueger , Fazl Barez

Sparse autoencoders (SAEs) offer a natural path toward comparable explanations across different representation spaces. However, current SAEs are trained per modality, producing dictionaries whose features are not directly understandable and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Difei Gu , Yunhe Gao , Gerasimos Chatzoudis , Zihan Dong , Guoning Zhang , Bangwei Guo , Yang Zhou , Mu Zhou , Dimitris Metaxas

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

Sparse autoencoders (SAEs) interpret neural network representations by decomposing activations into sparse combinations of dictionary atoms. However, SAEs assume features combine additively through linear reconstruction, an assumption that…

Machine Learning · Computer Science 2026-05-26 Panagiotis Koromilas , Andreas D. Demou , James Oldfield , Yannis Panagakis , Mihalis Nicolaou
‹ Prev 1 8 9 10 Next ›