English
Related papers

Related papers: Faithfulness and learning hypergraphs from discret…

200 papers

A confidence distribution is a complete tool for making frequentist inference for a parameter of interest $\psi$ based on an assumed parametric model. Indeed, it allows to reach point estimates, to assess their precision, to set up tests…

Methodology · Statistics 2022-12-20 Elena Bortolato , Laura Ventura

Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge. Many post-hoc concept-based approaches have been introduced to…

Machine Learning · Computer Science 2026-04-15 Amin Parchami-Araghi , Sukrut Rao , Jonas Fischer , Bernt Schiele

Machine learning models that operate on graph-structured data, such as molecular graphs or social networks, often make accurate predictions but offer little insight into why certain predictions are made. Counterfactual explanations address…

Machine Learning · Computer Science 2025-11-21 David Bechtoldt , Sidney Bender

Modern sociology has profoundly uncovered many convincing social criteria for behavioural analysis. Unfortunately, many of them are too subjective to be measured and presented in online social networks. On the other hand, data mining…

Social and Information Networks · Computer Science 2023-01-09 Xiangguo Sun , Hong Cheng , Bo Liu , Jia Li , Hongyang Chen , Guandong Xu , Hongzhi Yin

Graphs are fundamental data structures which concisely capture the relational structure in many important real-world domains, such as knowledge graphs, physical and social interactions, language, and chemistry. Here we introduce a powerful…

Machine Learning · Computer Science 2018-03-12 Yujia Li , Oriol Vinyals , Chris Dyer , Razvan Pascanu , Peter Battaglia

In the past, the dichotomy between homophily and heterophily has inspired research contributions toward a better understanding of Deep Graph Networks' inductive bias. In particular, it was believed that homophily strongly correlates with…

Machine Learning · Computer Science 2023-08-21 Daniele Castellana , Federico Errica

Graph structure learning aims to learn connectivity in a graph from data. It is particularly important for many computer vision related tasks since no explicit graph structure is available for images for most cases. A natural way to…

Computer Vision and Pattern Recognition · Computer Science 2022-12-26 Yaohua Wang , FangYi Zhang , Ming Lin , Senzhang Wang , Xiuyu Sun , Rong Jin

A common approach to explaining NLP models is to use importance measures that express which tokens are important for a prediction. Unfortunately, such explanations are often wrong despite being persuasive. Therefore, it is essential to…

Computation and Language · Computer Science 2024-08-29 Andreas Madsen , Siva Reddy , Sarath Chandar

Self-explainable deep neural networks are a recent class of models that can output ante-hoc local explanations that are faithful to the model's reasoning, and as such represent a step forward toward filling the gap between expressiveness…

Machine Learning · Computer Science 2023-08-30 Marc Christiansen , Lea Villadsen , Zhiqiang Zhong , Stefano Teso , Davide Mottin

Recent years have witnessed the emergence of a variety of post-hoc interpretations that aim to uncover how natural language processing (NLP) models make predictions. Despite the surge of new interpretation methods, it remains an open…

Computation and Language · Computer Science 2022-04-04 Fan Yin , Zhouxing Shi , Cho-Jui Hsieh , Kai-Wei Chang

While enjoying the great achievements brought by deep learning (DL), people are also worried about the decision made by DL models, since the high degree of non-linearity of DL models makes the decision extremely difficult to understand.…

Machine Learning · Computer Science 2023-09-13 Jinwen He , Kai Chen , Guozhu Meng , Jiangshan Zhang , Congyi Li

Modeling functions that are sequentially observed as functional time series is becoming increasingly common. In such models, it is often crucial to ensure data homogeneity. We investigate the sensitivity of graph-based change point…

Methodology · Statistics 2025-03-25 Jeremy VanderDoes , Shojaeddin Chenouri

How can we draw trustworthy scientific conclusions? One criterion is that a study can be replicated by independent teams. While replication is critically important, it is arguably insufficient. If a study is biased for some reason and other…

Methodology · Statistics 2025-02-06 Yujin Jeong , Dominik Rothenhäusler

In statistical network analysis, models for binary adjacency matrices satisfying vertex exchangeability are commonly used. However, such models may fail to capture key features of the data-generating process when interactions, rather than…

Methodology · Statistics 2025-09-03 Ayoushman Bhattacharya , Nilanjan Chakraborty , Robert Lunde

Hypergraphs naturally represent higher-order interactions, which persistently appear from social interactions to neural networks and other natural systems. Although their importance is well recognized, a theoretical framework to describe…

Physics and Society · Physics 2020-05-25 Guilherme Ferraz de Arruda , Michele Tizzani , Yamir Moreno

Networks and graphs provide a simple but effective model to a vast set of systems which building blocks interact throughout pairwise interactions. Unfortunately, such models fail to describe all those systems which building blocks interact…

Physics and Society · Physics 2022-09-21 Mauro Faccin

A covariance graph is an undirected graph associated with a multivariate probability distribution of a given random vector where each vertex represents each of the different components of the random vector and where the absence of an edge…

Probability · Mathematics 2009-12-15 Dhafer Malouche , Bala Rajaratnam

This paper develops new limit theory for data that are generated by networks or more generally display cross-sectional dependence structures that are governed by observable and unobservable characteristics. Strategic network formation…

Probability · Mathematics 2019-08-08 Guido M. Kuersteiner

Trusting machine learning algorithms requires having confidence in their outputs. Confidence is typically interpreted in terms of model reliability, where a model is reliable if it produces a high proportion of correct outputs. However,…

Machine Learning · Computer Science 2023-11-01 Jonathan Vandenburgh

Attention mechanisms are dominating the explainability of deep models. They produce probability distributions over the input, which are widely deemed as feature-importance indicators. However, in this paper, we find one critical limitation…

Machine Learning · Computer Science 2022-07-06 Yibing Liu , Haoliang Li , Yangyang Guo , Chenqi Kong , Jing Li , Shiqi Wang