Related papers: Shadow Datasets, New challenging datasets for Caus…

Visual Commonsense Reasoning (VCR) refers to answering questions and providing explanations based on images. While existing methods achieve high prediction accuracy, they often overlook bias in datasets and lack debiasing strategies. In…

Learning behavioral patterns from observational data has been a de-facto approach to motion forecasting. Yet, the current paradigm suffers from two shortcomings: brittle under distribution shifts and inefficient for knowledge transfer. In…

Reinforcement Learning (RL) is an important machine learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in this field due to the rapid development of deep neural networks.…

We introduce Consistent Assignment for Representation Learning (CARL), an unsupervised learning method to learn visual representations by combining ideas from self-supervised contrastive learning and deep clustering. By viewing contrastive…

Visual recognition tasks are often limited to dealing with a small subset of classes simply because the labels for the remaining classes are unavailable. We are interested in identifying novel concepts in a dataset through representation…

Context-aware methods achieved great success in supervised scene text recognition via incorporating semantic priors from words. We argue that such prior contextual information can be interpreted as the relations of textual primitives due to…

Contrastive learning has shown effectiveness in improving sequential recommendation models. However, existing methods still face challenges in generating high-quality contrastive pairs: they either rely on random perturbations that corrupt…

The goal of Fair Representation Learning (FRL) is to mitigate biases in machine learning models by learning data representations that enable high accuracy on downstream tasks while minimizing discrimination based on sensitive attributes.…

Acquiring the most representative examples via active learning (AL) can benefit many data-dependent computer vision tasks by minimizing efforts of image-level or pixel-wise annotations. In this paper, we propose a novel Collaborative…

Learning causal relationships from time series data is an important but challenging problem. Existing synthetic datasets often contain hidden artifacts that can be exploited by causal discovery methods, reducing their usefulness for…

Link prediction on graphs is a fundamental problem. Subgraph representation learning approaches (SGRLs), by transforming link prediction to graph classification on the subgraphs around the links, have achieved state-of-the-art performance…

Conversational semantic role labeling (CSRL) is a newly proposed task that uncovers the shallow semantic structures in a dialogue text. Unfortunately several important characteristics of the CSRL task have been overlooked by the existing…

An improved understanding of soil can enable more sustainable land-use practices. Nevertheless, soil is called a complex, living medium due to the complex interaction of different soil processes that limit our understanding of soil.…

Machine Learning (ML) has become an integral aspect of many real-world applications. As a result, the need for responsible machine learning has emerged, focusing on aligning ML models to ethical and social values, while enhancing their…

Causal datasets play a critical role in advancing the field of causality. However, existing datasets often lack the complexity of real-world issues such as selection bias, unfaithful data, and confounding. To address this gap, we propose a…

Disentangled representation learning (DRL) aims to identify and decompose underlying factors behind observations, thus facilitating data perception and generation. However, current DRL approaches often rely on the unrealistic assumption…

Continuous unsupervised representation learning (CURL) research has greatly benefited from improvements in self-supervised learning (SSL) techniques. As a result, existing CURL methods using SSL can learn high-quality representations…

Despite the multifaceted recent advances in interventional causal representation learning (CRL), they primarily focus on the stylized assumption of single-node interventions. This assumption is not valid in a wide range of applications, and…

With the rise of deep learning algorithms nowadays, scene image representation methods have achieved a significant performance boost in classification. However, the performance is still limited because the scene images are mostly complex…

Randomised controlled trials (RCTs) are the most effective approach to causal discovery, but in many circumstances it is impossible to conduct RCTs. Therefore observational studies based on passively observed data are widely accepted as an…