English
Related papers

Related papers: Explaining Generalization Power of a DNN Using Int…

200 papers

This paper aims to analyze the generalization power of deep neural networks (DNNs) from the perspective of interactions. Unlike previous analysis of a DNN's generalization power in a highdimensional feature space, we find that the…

Machine Learning · Computer Science 2025-02-17 Lei Cheng , Junpeng Zhang , Qihan Ren , Quanshi Zhang

This paper proposes a new perspective for analyzing the generalization power of deep neural networks (DNNs), i.e., directly disentangling and analyzing the dynamics of generalizable and non-generalizable interaction encoded by a DNN through…

Machine Learning · Computer Science 2025-05-21 Yuxuan He , Junpeng Zhang , Lei Cheng , Hongyuan Zhang , Quanshi Zhang

Faithfully summarizing the knowledge encoded by a deep neural network (DNN) into a few symbolic primitive patterns without losing much information represents a core challenge in explainable AI. To this end, Ren et al. (2024) have derived a…

Machine Learning · Computer Science 2024-09-16 Lu Chen , Siyu Lou , Benhao Huang , Quanshi Zhang

This paper explores the bottleneck of feature representations of deep neural networks (DNNs), from the perspective of the complexity of interactions between input variables encoded in DNNs. To this end, we focus on the multi-order…

Machine Learning · Computer Science 2022-11-08 Huiqi Deng , Qihan Ren , Hao Zhang , Quanshi Zhang

This paper aims to explain how a deep neural network (DNN) gradually extracts new knowledge and forgets noisy features through layers in forward propagation. Up to now, although the definition of knowledge encoded by the DNN has not reached…

Machine Learning · Computer Science 2024-09-16 Xu Cheng , Lei Cheng , Zhaoran Peng , Yang Xu , Tian Han , Quanshi Zhang

In this paper, we find that the complexity of interactions encoded by a deep neural network (DNN) can explain its generalization power. We also discover that the confusing samples of a DNN, which are represented by non-generalizable…

Machine Learning · Computer Science 2025-02-13 Junpeng Zhang , Lei Cheng , Qing Li , Liang Lin , Quanshi Zhang

Recently, a series of studies have tried to extract interactions between input variables modeled by a DNN and define such interactions as concepts encoded by the DNN. However, strictly speaking, there still lacks a solid guarantee whether…

Machine Learning · Computer Science 2024-09-16 Mingjie Li , Quanshi Zhang

Understanding what kinds of cooperative structures deep neural networks (DNNs) can represent remains a fundamental yet insufficiently understood problem. In this work, we treat interactions as the fundamental units of such structure and…

Machine Learning · Computer Science 2025-12-23 Huiqi Deng , Qihan Ren , Zhuofan Chen , Zhenyuan Cui , Wen Shen , Peng Zhang , Hongbin Pei , Quanshi Zhang

In this paper, we focus on mean-field variational Bayesian Neural Networks (BNNs) and explore the representation capacity of such BNNs by investigating which types of concepts are less likely to be encoded by the BNN. It has been observed…

Machine Learning · Computer Science 2023-12-04 Qihan Ren , Huiqi Deng , Yunuo Chen , Siyu Lou , Quanshi Zhang

Deep neural networks (DNNs) with high expressiveness have achieved state-of-the-art performance in many tasks. However, their distributed feature representations are difficult to interpret semantically. In this work, human-interpretable…

Computer Vision and Pattern Recognition · Computer Science 2019-10-22 Jindong Gu , Volker Tresp

In this paper, we rethink how a DNN encodes visual concepts of different complexities from a new perspective, i.e. the game-theoretic multi-order interactions between pixels in an image. Beyond the categorical taxonomy of objects and the…

Machine Learning · Computer Science 2021-06-22 Xu Cheng , Chuntung Chu , Yi Zheng , Jie Ren , Quanshi Zhang

This study proves the two-phase dynamics of a deep neural network (DNN) learning interactions. Despite the long disappointing view of the faithfulness of post-hoc explanation of a DNN, a series of theorems have been proven in recent years…

Machine Learning · Computer Science 2024-11-26 Qihan Ren , Junpeng Zhang , Yang Xu , Yue Xin , Dongrui Liu , Quanshi Zhang

Deep neural networks (DNNs) have demonstrated impressive performance on a wide array of tasks, but they are usually considered opaque since internal structure and learned parameters are not interpretable. In this paper, we re-examine the…

Computer Vision and Pattern Recognition · Computer Science 2017-08-21 Yinpeng Dong , Hang Su , Jun Zhu , Fan Bao

This paper investigates the dynamics of a deep neural network (DNN) learning interactions. Previous studies have discovered and mathematically proven that given each input sample, a well-trained DNN usually only encodes a small number of…

Machine Learning · Computer Science 2024-05-17 Junpeng Zhang , Qing Li , Liang Lin , Quanshi Zhang

A robust theoretical framework that can describe and predict the generalization ability of deep neural networks (DNNs) in general circumstances remains elusive. Classical attempts have produced complexity metrics that rely heavily on global…

Machine Learning · Computer Science 2020-01-20 Marelie H. Davel , Marthinus W. Theunissen , Arnold M. Pretorius , Etienne Barnard

Graph neural networks (GNNs) are highly effective on a variety of graph-related tasks; however, they lack interpretability and transparency. Current explainability approaches are typically local and treat GNNs as black-boxes. They do not…

Machine Learning · Computer Science 2023-03-10 Han Xuanyuan , Pietro Barbiero , Dobrik Georgiev , Lucie Charlotte Magister , Pietro Lió

Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose…

Computer Vision and Pattern Recognition · Computer Science 2017-03-31 Yinpeng Dong , Hang Su , Jun Zhu , Bo Zhang

One hypothesis for the success of deep neural networks (DNNs) is that they are highly expressive, which enables them to be applied to many problems, and they have a strong inductive bias towards solutions that are simple, known as…

Quantum Physics · Physics 2024-07-04 Jessica Pointing

Deep Neural Networks (DNNs) achieve state-of-the-art performance on numerous applications. However, it is difficult to tell beforehand if a DNN receiving an input will deliver the correct output since their decision criteria are usually…

Machine Learning · Computer Science 2021-09-07 Julia Lust , Alexandru Paul Condurache

This paper focuses on the domain generalization task where domain knowledge is unavailable, and even worse, only samples from a single domain can be utilized during training. Our motivation originates from the recent progresses in deep…

Machine Learning · Computer Science 2022-03-08 Chris Xing Tian , Haoliang Li , Xiaofei Xie , Yang Liu , Shiqi Wang
‹ Prev 1 2 3 10 Next ›