English
Related papers

Related papers: The Architectural Bottleneck Principle

200 papers

Deep learning representations are often difficult to interpret, which can hinder their deployment in sensitive applications. Concept Bottleneck Models (CBMs) have emerged as a promising approach to mitigate this issue by learning…

Machine Learning · Computer Science 2026-01-30 Antonio Almudévar , José Miguel Hernández-Lobato , Alfonso Ortega

The Information Bottleneck (IB) principle has emerged as a promising approach for enhancing the generalization, robustness, and interpretability of deep neural networks, demonstrating efficacy across image segmentation, document clustering,…

Information Theory · Computer Science 2025-04-18 Hanzhe Yang , Youlong Wu , Dingzhu Wen , Yong Zhou , Yuanming Shi

Sample efficiency is a crucial property of language models with practical implications for training efficiency. In real-world text, information follows a long-tailed distribution. Yet, we expect models to learn and recall frequent and…

Computation and Language · Computer Science 2025-06-23 Daniel Christoph , Max Ploner , Patrick Haller , Alan Akbik

Attribution methods provide insights into the decision-making of machine learning models like artificial neural networks. For a given input sample, they assign a relevance score to each individual input variable, such as the pixels of an…

Machine Learning · Statistics 2020-05-26 Karl Schulz , Leon Sixt , Federico Tombari , Tim Landgraf

Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by constructing and explaining their predictions using a set of high-level concepts. A special property of these models is that they permit concept interventions,…

The Information Bottleneck (IB) method is an information theoretical framework to design a parsimonious and tunable feature-extraction mechanism, such that the extracted features are maximally relevant to a specific learning or inference…

Signal Processing · Electrical Eng. & Systems 2024-04-17 Francesco Binucci , Paolo Banelli , Paolo Di Lorenzo , Sergio Barbarossa

Concept Bottleneck Models (CBMs) first map raw input(s) to a vector of human-defined concepts, before using this vector to predict a final classification. We might therefore expect CBMs capable of predicting concepts based on distinct…

Artificial Intelligence · Computer Science 2023-02-08 Jack Furby , Daniel Cunnington , Dave Braines , Alun Preece

Introducing attentional mechanism in neural network is a powerful concept, and has achieved impressive results in many natural language processing tasks. However, most of the existing models impose attentional distribution on a flat…

Computation and Language · Computer Science 2016-07-25 PengFei Liu , Xipeng Qiu , Xuanjing Huang

The success of neural networks on a diverse set of NLP tasks has led researchers to question how much these networks actually ``know'' about natural language. Probes are a natural way of assessing this. When probing, a researcher chooses a…

Computation and Language · Computer Science 2020-05-26 Tiago Pimentel , Josef Valvoda , Rowan Hall Maudslay , Ran Zmigrod , Adina Williams , Ryan Cotterell

We consider the problem of learning a neural network classifier. Under the information bottleneck (IB) principle, we associate with this classification problem a representation learning problem, which we call "IB learning". We show that IB…

Machine Learning · Computer Science 2021-06-02 Masoumeh Soflaei , Hongyu Guo , Ali Al-Bashabsheh , Yongyi Mao , Richong Zhang

The selective visual attention mechanism in the human visual system (HVS) restricts the amount of information to reach visual awareness for perceiving natural scenes, allowing near real-time information processing with limited computational…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Qiuxia Lai , Yu Li , Ailing Zeng , Minhao Liu , Hanqiu Sun , Qiang Xu

Concept Bottleneck Models (CBMs) aim to deliver interpretable predictions by routing decisions through a human-understandable concept layer, yet they often suffer reduced accuracy and concept leakage that undermines faithfulness. We…

Machine Learning · Computer Science 2026-02-17 Karim Galliamov , Syed M Ahsan Kazmi , Adil Khan , Adín Ramírez Rivera

Analysing whether neural language models encode linguistic information has become popular in NLP. One method of doing so, which is frequently cited to support the claim that models like BERT encode syntax, is called probing; probes are…

Computation and Language · Computer Science 2021-06-07 Rowan Hall Maudslay , Ryan Cotterell

With the recent success of pre-trained models in NLP, a significant focus was put on interpreting their representations. One of the most prominent approaches is structural probing (Hewitt and Manning, 2019), where a linear projection of…

Computation and Language · Computer Science 2021-06-25 Tomasz Limisiewicz , David Mareček

Humor is prevalent in online communications and it often relies on more than one modality (e.g., cartoons and memes). Interpreting humor in multimodal settings requires drawing on diverse types of knowledge, including metaphorical,…

Computation and Language · Computer Science 2025-10-06 EunJeong Hwang , Peter West , Vered Shwartz

The information bottleneck (IB) principle has been suggested as a way to analyze deep neural networks. The learning dynamics are studied by inspecting the mutual information (MI) between the hidden layers and the input and output. Notably,…

Machine Learning · Computer Science 2022-02-15 Stephan Sloth Lorenzen , Christian Igel , Mads Nielsen

Machine learning tasks are generally formulated as optimization problems, where one searches for an optimal function within a certain functional space. In practice, parameterized functional spaces are considered, in order to be able to…

Artificial Intelligence · Computer Science 2024-12-13 Manon Verbockhaven , Sylvain Chevallier , Guillaume Charpiat , Théo Rudkiewicz

This paper presents an unsupervised extractive approach to summarize scientific long documents based on the Information Bottleneck principle. Inspired by previous work which uses the Information Bottleneck principle for sentence…

Computation and Language · Computer Science 2021-10-05 Jiaxin Ju , Ming Liu , Huan Yee Koh , Yuan Jin , Lan Du , Shirui Pan

It is commonly believed that knowledge of syntactic structure should improve language modeling. However, effectively and computationally efficiently incorporating syntactic structure into neural language models has been a challenging topic.…

Computation and Language · Computer Science 2020-05-13 Wenyu Du , Zhouhan Lin , Yikang Shen , Timothy J. O'Donnell , Yoshua Bengio , Yue Zhang

In this theory paper, we investigate training deep neural networks (DNNs) for classification via minimizing the information bottleneck (IB) functional. We show that the resulting optimization problem suffers from two severe issues: First,…

Machine Learning · Computer Science 2020-08-10 Rana Ali Amjad , Bernhard C. Geiger