English
Related papers

Related papers: The Causal Structure of Domain Invariant Supervise…

200 papers

We discuss recent work for causal inference and predictive robustness in a unifying way. The key idea relies on a notion of probabilistic invariance or stability: it opens up new insights for formulating causality as a certain risk…

Methodology · Statistics 2018-12-21 Peter Bühlmann

At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…

Machine Learning · Computer Science 2024-05-29 Sharut Gupta , Chenyu Wang , Yifei Wang , Tommi Jaakkola , Stefanie Jegelka

This paper investigates the problem of learning robust, generalizable prediction models from a combination of multiple datasets and qualitative assumptions about the underlying data-generating model. Part of the challenge of learning robust…

Machine Learning · Statistics 2022-02-04 Alexis Bellot , Mihaela van der Schaar

The data-driven approach to robot control has been gathering pace rapidly, yet generalization to unseen task domains remains a critical challenge. We argue that the key to generalization is representations that are (i) rich enough to…

Robotics · Computer Science 2023-12-05 Bo Ai , Zhanxin Wu , David Hsu

We propose an architecture for training generative models of counterfactual conditionals of the form, 'can we modify event A to cause B instead of C?', motivated by applications in robot control. Using an 'adversarial training' paradigm, an…

Robotics · Computer Science 2020-09-23 Simón C. Smith , Subramanian Ramamoorthy

A common technique for verifying the safety of complex systems is the inductive invariant method. Inductive invariants are inductive formulas that overapproximate the reachable states of a system and imply a desired safety property.…

Logic in Computer Science · Computer Science 2025-09-09 Ian Dardik , Eunsuk Kang

Counterfactual explanations are widely used to interpret machine learning predictions by identifying minimal changes to input features that would alter a model's decision. However, most existing counterfactual methods have not been tested…

Machine Learning · Computer Science 2026-02-03 Leonidas Christodoulou , Chang Sun

Developing robust and interpretable vision systems is a crucial step towards trustworthy artificial intelligence. In this regard, a promising paradigm considers embedding task-required invariant structures, e.g., geometric invariance, in…

Computer Vision and Pattern Recognition · Computer Science 2024-04-12 Shuren Qi , Yushu Zhang , Chao Wang , Zhihua Xia , Xiaochun Cao , Jian Weng

Investigation of machine learning algorithms robust to changes between the training and test distributions is an active area of research. In this paper we explore a special type of dataset shift which we call class-dependent domain shift.…

Machine Learning · Computer Science 2020-07-13 Tigran Galstyan , Hrant Khachatrian , Greg Ver Steeg , Aram Galstyan

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…

Learning the causal structure behind data is invaluable for improving generalization and obtaining high-quality explanations. We propose a novel framework, Invariant Structure Learning (ISL), that is designed to improve causal structure…

Machine Learning · Computer Science 2022-06-15 Yunhao Ge , Sercan Ö. Arik , Jinsung Yoon , Ao Xu , Laurent Itti , Tomas Pfister

We consider representation learning (hypothesis class $\mathcal{H} = \mathcal{F}\circ\mathcal{G}$) where training and test distributions can be different. Recent studies provide hints and failure examples for domain invariant representation…

Machine Learning · Computer Science 2020-06-05 Xi Wu , Yang Guo , Jiefeng Chen , Yingyu Liang , Somesh Jha , Prasad Chalasani

The two fields of machine learning and graphical causality arose and developed separately. However, there is now cross-pollination and increasing interest in both fields to benefit from the advances of the other. In the present paper, we…

Domain shifts in the training data are common in practical applications of machine learning; they occur for instance when the data is coming from different sources. Ideally, a ML model should work well independently of these shifts, for…

Medical imaging models frequently fail when deployed across hospitals, scanners, populations, or imaging protocols due to domain shift, limiting their clinical reliability. While transfer learning and domain adaptation address such shifts…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Mohammed M. Abdelsamea , Daniel Tweneboah Anyimadu , Tasneem Selim , Saif Alzubi , Lei Zhang , Ahmed Karam Eldaly , Xujiong Ye

We propose methods to strengthen the invariance properties of representations obtained by contrastive learning. While existing approaches implicitly induce a degree of invariance as representations are learned, we look to more directly…

Machine Learning · Computer Science 2021-03-23 Adam Foster , Rattana Pukdee , Tom Rainforth

Despite tremendous progress over the past decade, deep learning methods generally fall short of human-level systematic generalization. It has been argued that explicitly capturing the underlying structure of data should allow connectionist…

Machine Learning · Computer Science 2023-04-26 Andrea Dittadi

The goal of causal representation learning is to find a representation of data that consists of causally related latent variables. We consider a setup where one has access to data from multiple domains that potentially share a causal…

Machine Learning · Statistics 2023-10-30 Nils Sturma , Chandler Squires , Mathias Drton , Caroline Uhler

Recently, with the significant developments in deep learning techniques, solving underdetermined inverse problems has become one of the major concerns in the medical imaging domain. Typical examples include undersampled magnetic resonance…

Image and Video Processing · Electrical Eng. & Systems 2020-06-29 Chang Min Hyun , Seong Hyeon Baek , Mingyu Lee , Sung Min Lee , Jin Keun Seo

In real-life applications, machine learning models often face scenarios where there is a change in data distribution between training and test domains. When the aim is to make predictions on distributions different from those seen at…

Machine Learning · Computer Science 2021-11-04 Lucas Mansilla , Rodrigo Echeveste , Diego H. Milone , Enzo Ferrante
‹ Prev 1 3 4 5 6 7 10 Next ›