English
Related papers

Related papers: Enhancing Neural Network Interpretability Through …

200 papers

Existing recurrent optical flow estimation networks are computationally expensive since they use a fixed large number of iterations to update the flow field for each sample. An efficient network should skip iterations when the flow…

Computer Vision and Pattern Recognition · Computer Science 2024-01-08 Ri Cheng , Ruian He , Xuhao Jiang , Shili Zhou , Weimin Tan , Bo Yan

The Information Bottleneck (IB) framework is a general characterization of optimal representations obtained using a principled approach for balancing accuracy and complexity. Here we present a new framework, the Dual Information Bottleneck…

Information Theory · Computer Science 2020-06-09 Zoe Piran , Ravid Shwartz-Ziv , Naftali Tishby

This paper proposes a deep representation learning using an information-theoretic loss with an aim to increase the inter-class distances as well as within-class similarity in the embedded space. Tasks such as anomaly and out-of-distribution…

Machine Learning · Computer Science 2022-02-08 Shin Ando

In an attempt to gather a deeper understanding of how convolutional neural networks (CNNs) reason about human-understandable concepts, we present a method to infer labeled concept data from hidden layer activations and interpret the…

Machine Learning · Computer Science 2019-06-18 Conner Chyung , Michael Tsang , Yan Liu

Recent advances in interpretability suggest we can project weights and hidden states of transformer-based language models (LMs) to their vocabulary, a transformation that makes them more human interpretable. In this paper, we investigate LM…

Computation and Language · Computer Science 2023-11-27 Shahar Katz , Yonatan Belinkov

Active learning aims to select samples to be annotated that yield the largest performance improvement for the learning algorithm. Many methods approach this problem by measuring the informativeness of samples and do this based on the…

Machine Learning · Computer Science 2021-08-02 Javad Zolfaghari Bengar , Bogdan Raducanu , Joost van de Weijer

The Information bottleneck method is an unsupervised non-parametric data organization technique. Given a joint distribution P(A,B), this method constructs a new variable T that extracts partitions, or clusters, over the values of A that are…

Machine Learning · Computer Science 2013-01-14 Nir Friedman , Ori Mosenzon , Noam Slonim , Naftali Tishby

In this study, we investigate the under-explored intervention planning aimed at disseminating accurate information within dynamic opinion networks by leveraging learning strategies. Intervention planning involves identifying key nodes…

Machine Learning · Computer Science 2024-11-05 Bharath Muppasani , Protik Nag , Vignesh Narayanan , Biplav Srivastava , Michael N. Huhns

The emergence of Graph Convolutional Network (GCN) has greatly boosted the progress of graph learning. However, two disturbing factors, noise and redundancy in graph data, and lack of interpretation for prediction results, impede further…

Machine Learning · Computer Science 2021-03-23 Junchi Yu , Tingyang Xu , Yu Rong , Yatao Bian , Junzhou Huang , Ran He

Continual learning aims to update models under distribution shift without forgetting, yet many high-stakes deployments, such as healthcare, also require interpretability. In practice, models that adapt well (e.g., deep networks) are often…

Machine Learning · Computer Science 2026-04-21 Dongkyu Cho , Xiyue Li , Samrachana Adhikari , Rumi Chunara

Concept bottleneck models have been successfully used for explainable machine learning by encoding information within the model with a set of human-defined concepts. In the context of human-assisted or autonomous driving, explainability…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Jessica Echterhoff , An Yan , Kyungtae Han , Amr Abdelraouf , Rohit Gupta , Julian McAuley

Graph knowledge models and ontologies are very powerful modeling and re asoning tools. We propose an effective approach to model network attacks and attack prediction which plays important roles in security management. The goals of this…

Artificial Intelligence · Computer Science 2013-04-04 Ahmad Salahi , Morteza Ansarinia

Network science enables the effective analysis of real interconnected systems, characterized by a complex interplay between topology and interconnections strength. It is well-known that the topology of a network affects its resilience to…

Physics and Society · Physics 2021-06-10 Giulia Bertagnolli , Riccardo Gallotti , Manlio De Domenico

Although neural models have achieved remarkable performance, they still encounter doubts due to the intransparency. To this end, model prediction explanation is attracting more and more attentions. However, current methods rarely…

Computer Vision and Pattern Recognition · Computer Science 2024-01-30 Yong Guan , Freddy Lecue , Jiaoyan Chen , Ru Li , Jeff Z. Pan

This paper presents a novel learning analytics method: Transition Network Analysis (TNA), a method that integrates Stochastic Process Mining and probabilistic graph representation to model, visualize, and identify transition patterns in the…

Social and Information Networks · Computer Science 2025-02-06 Mohammed Saqr , Sonsoles López-Pernas , Tiina Törmänen , Rogers Kaliisa , Kamila Misiejuk , Santtu Tikka

The reasonable definition of semantic interpretability presents the core challenge in explainable AI. This paper proposes a method to modify a traditional convolutional neural network (CNN) into an interpretable compositional CNN, in order…

Computer Vision and Pattern Recognition · Computer Science 2021-07-12 Wen Shen , Zhihua Wei , Shikun Huang , Binbin Zhang , Jiaqi Fan , Ping Zhao , Quanshi Zhang

The presence of symmetries imposes a stringent set of constraints on a system. This constrained structure allows intelligent agents interacting with such a system to drastically improve the efficiency of learning and generalization, through…

Information Theory · Computer Science 2024-10-03 Hippolyte Charvin , Nicola Catenacci Volpi , Daniel Polani

Despite substantial efforts, neural network interpretability remains an elusive goal, with previous research failing to provide succinct explanations of most single neurons' impact on the network output. This limitation is due to the…

Machine Learning · Computer Science 2024-02-01 Simon C. Marshall , Jan H. Kirchner

Conventional machine learning methods are predominantly designed to predict outcomes based on a single data type. However, practical applications may encompass data of diverse types, such as text, images, and audio. We introduce…

The problem of attributing a deep network's prediction to its \emph{input/base} features is well-studied. We introduce the notion of \emph{conductance} to extend the notion of attribution to the understanding the importance of \emph{hidden}…

Machine Learning · Computer Science 2018-06-01 Kedar Dhamdhere , Mukund Sundararajan , Qiqi Yan