相关论文: ML4C: Seeing Causality Through Latent Vicinity

As a newly emerging unsupervised learning paradigm, self-supervised learning (SSL) recently gained widespread attention, which usually introduces a pretext task without manual annotation of data. With its help, SSL effectively learns the…

The goal of Causal Discovery is to find automated search methods for learning causal structures from observational data. In some cases all variables of the interested causal mechanism are measured, and the task is to predict the effects one…

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks…

Supervised dictionary learning (SDL) is a classical machine learning method that simultaneously seeks feature extraction and classification tasks, which are not necessarily a priori aligned objectives. The goal of SDL is to learn a…

Recent advancements in unsupervised domain adaptation (UDA) and semi-supervised learning (SSL), particularly incorporating causality, have led to significant methodological improvements in these learning problems. However, a formal theory…

Language-supervised vision models have recently attracted great attention in computer vision. A common approach to build such models is to use contrastive learning on paired data across the two modalities, as exemplified by Contrastive…

Semi-supervised learning (SSL), which aims at leveraging a few labeled images and a large number of unlabeled images for network training, is beneficial for relieving the burden of data annotation in medical image segmentation. According to…

Discovering causal relationships in complex multivariate time series is a fundamental scientific challenge. Traditional methods often falter, either by relying on restrictive linear assumptions or on conditional independence tests that…

In this work, we present Multi-Level Contrastive Learning for Dense Prediction Task (MCL), an efficient self-supervised method for learning region-level feature representation for dense prediction tasks. Our method is motivated by the three…

Machine learning (ML) research has yielded powerful tools for training accurate prediction models despite complex multivariate associations (e.g. interactions and heterogeneity). In fields such as medicine, improved interpretability of ML…

Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions. Yet, existing efforts are largely limited to simple synthetic settings that are far away from…

In this article, we describe the algorithms for causal structure learning from time series data that won the Causality 4 Climate competition at the Conference on Neural Information Processing Systems 2019 (NeurIPS). We examine how our…

Discovering causal relationships from observational data, particularly in the presence of latent variables, poses a challenging problem. While current local structure learning methods have proven effective and efficient when the focus lies…

Vision-and-Language Navigation (VLN) has gained significant research interest in recent years due to its potential applications in real-world scenarios. However, existing VLN methods struggle with the issue of spurious associations,…

We present a workflow for clinical data analysis that relies on Bayesian Structure Learning (BSL), an unsupervised learning approach, robust to noise and biases, that allows to incorporate prior medical knowledge into the learning process…

Causal discovery from time series data encompasses many existing solutions, including those based on deep learning techniques. However, these methods typically do not endorse one of the most prevalent paradigms in deep learning: End-to-end…

Learning with supervision has achieved remarkable success in numerous artificial intelligence (AI) applications. In the current literature, by referring to the properties of the labels prepared for the training dataset, learning with…

Semi-Supervised Learning (SSL) and Unsupervised Domain Adaptation (UDA) enhance the model performance by exploiting information from labeled and unlabeled data. The clustering assumption has proven advantageous for learning with limited…

The cross-pollination between causal discovery and deep learning has led to increasingly extensive interactions. It results in a large number of deep learning data types (such as images, text, etc.) extending into the field of causal…

Causal representation learning (CRL) seeks to uncover meaningful latent variables and their corresponding causal structure from high-dimensional observational data. Although its significance, CRL identifiability remains a crucial property,…