English
Related papers

Related papers: A Generalized Information Bottleneck Theory of Dee…

200 papers

Graph pooling is an essential ingredient of Graph Neural Networks (GNNs) in graph classification and regression tasks. For these tasks, different pooling strategies have been proposed to generate a graph-level representation by downsampling…

Machine Learning · Computer Science 2021-04-28 Kashob Kumar Roy , Amit Roy , A K M Mahbubur Rahman , M Ashraful Amin , Amin Ahsan Ali

Recent studies have revealed that GNNs are vulnerable to adversarial attacks. Most existing robust graph learning methods measure model robustness based on label information, rendering them infeasible when label information is not…

Machine Learning · Computer Science 2023-06-09 Jihong Wang , Minnan Luo , Jundong Li , Ziqi Liu , Jun Zhou , Qinghua Zheng

This paper presents Hyper-VIB, a hypernetwork-enhanced information bottleneck (IB) approach designed to enable efficient task-oriented communications in 6G collaborative intelligent systems. Leveraging IB theory, our approach enables an…

Information Theory · Computer Science 2025-11-20 Jingchen Peng , Chaowen Deng , Yili Deng , Boxiang Ren , Lu Yang

Graph Neural Networks (GNNs) have achieved great success in modeling graph-structured data. However, recent works show that GNNs are vulnerable to adversarial attacks which can fool the GNN model to make desired predictions of the attacker.…

Machine Learning · Computer Science 2023-06-16 Enyan Dai , Limeng Cui , Zhengyang Wang , Xianfeng Tang , Yinghan Wang , Monica Cheng , Bing Yin , Suhang Wang

The Symmetric Information Bottleneck (SIB), an extension of the more familiar Information Bottleneck, is a dimensionality reduction technique that simultaneously compresses two random variables to preserve information between their…

Information Theory · Computer Science 2024-02-06 K. Michael Martini , Ilya Nemenman

Numerous deep learning algorithms have been inspired by and understood via the notion of information bottleneck, where unnecessary information is (often implicitly) minimized while task-relevant information is maximized. However, a rigorous…

Machine Learning · Computer Science 2023-05-31 Kenji Kawaguchi , Zhun Deng , Xu Ji , Jiaoyang Huang

We address the question of characterizing and finding optimal representations for supervised learning. Traditionally, this question has been tackled using the Information Bottleneck, which compresses the inputs while retaining information…

Machine Learning · Computer Science 2021-07-19 Yann Dubois , Douwe Kiela , David J. Schwab , Ramakrishna Vedantam

The Information Bottleneck (IB) principle facilitates effective representation learning by preserving label-relevant information while compressing irrelevant information. However, its strong reliance on accurate labels makes it inherently…

Machine Learning · Computer Science 2025-12-12 Yi Huang , Qingyun Sun , Yisen Gao , Haonan Yuan , Xingcheng Fu , Jianxin Li

Much of the field of Machine Learning exhibits a prominent set of failure modes, including vulnerability to adversarial examples, poor out-of-distribution (OoD) detection, miscalibration, and willingness to memorize random labelings of…

Machine Learning · Computer Science 2023-07-19 Ian Fischer

Compact neural networks are essential for affordable and power efficient deep learning solutions. Binary Neural Networks (BNNs) take compactification to the extreme by constraining both weights and activations to two levels, $\{+1, -1\}$.…

Machine Learning · Computer Science 2020-06-16 Vishnu Raj , Nancy Nayak , Sheetal Kalyani

In recent several years, the information bottleneck (IB) principle provides an information-theoretic framework for deep multi-view clustering (MVC) by compressing multi-view observations while preserving the relevant information of multiple…

Information Theory · Computer Science 2024-03-26 Xiaoqiang Yan , Zhixiang Jin , Fengshou Han , Yangdong Ye

Molecular dynamics simulations offer detailed insights into atomic motions but face timescale limitations. Enhanced sampling methods have addressed these challenges but even with machine learning, they often rely on pre-selected…

Machine Learning · Computer Science 2024-09-19 Ziyue Zou , Dedi Wang , Pratyush Tiwary

In the Information Bottleneck (IB), when tuning the relative strength between compression and prediction terms, how do the two terms behave, and what's their relationship with the dataset and the learned representation? In this paper, we…

Machine Learning · Computer Science 2020-01-08 Tailin Wu , Ian Fischer

We propose a unified information-geometric framework that formalizes understanding in learning as a trade-off between informativeness and geometric simplicity. An encoder phi is evaluated by U(phi) = I(phi(X); Y) - beta * C(phi), where…

Machine Learning · Computer Science 2025-11-05 Ronald Katende

With the rapid emergence of multi-behavior learning in recommender systems, leveraging auxiliary user behaviors has proven effective for mitigating target-behavior data sparsity. Yet auxiliary behavior graphs frequently contain noisy or…

Information Retrieval · Computer Science 2026-05-26 Likang Wu , Zihao Chen , Jianxin Zhang , Sangqi Zhu , Yuanyuan Ge , Haipeng Yang , Lei Zhang

Information bottleneck (IB) principle [1] has become an important element in information-theoretic analysis of deep models. Many state-of-the-art generative models of both Variational Autoencoder (VAE) [2; 3] and Generative Adversarial…

Computer Vision and Pattern Recognition · Computer Science 2019-12-06 Slava Voloshynovskiy , Mouad Kondah , Shideh Rezaeifar , Olga Taran , Taras Holotyak , Danilo Jimenez Rezende

Graph neural networks (GNNs) are prominent for their effectiveness in processing graph data for semi-supervised node classification tasks. Most works of GNNs assume that the observed structure accurately represents the underlying node…

Machine Learning · Computer Science 2024-11-08 Shuangjie Li , Jiangqing Song , Baoming Zhang , Gaoli Ruan , Junyuan Xie , Chongjun Wang

The empirical studies of Graph Neural Networks (GNNs) broadly take the original node feature and adjacency relationship as singleview input, ignoring the rich information of multiple graph views. To circumvent this issue, the multiview…

Machine Learning · Computer Science 2022-10-13 Xiaolong Fan , Maoguo Gong , Yue Wu , Mingyang Zhang , Hao Li , Xiangming Jiang

Self-supervised learning has achieved remarkable empirical success in learning robust representations without explicit labels, most recently demonstrated within the framework of Joint-Embedding Predictive Architectures (JEPA). However, a…

Information Theory · Computer Science 2026-05-05 Yuval Domb

Temporal graph learning is crucial for dynamic networks where nodes and edges evolve over time and new nodes continuously join the system. Inductive representation learning in such settings faces two major challenges: effectively…

Machine Learning · Computer Science 2025-08-21 Jiafeng Xiong , Rizos Sakellariou