Related papers: Causal Disentanglement for Semantics-Aware Intent …

Causality knowledge is vital to building robust AI systems. Deep learning models often perform poorly on tasks that require causal reasoning, which is often derived using some form of commonsense knowledge not immediately available in the…

Disentangled Representation Learning aims to improve the explainability of deep learning methods by training a data encoder that identifies semantically meaningful latent variables in the data generation process. Nevertheless, there is no…

This paper proposes a new approach to training recommender systems called deviation-based learning. The recommender and rational users have different knowledge. The recommender learns user knowledge by observing what action users take upon…

Modeling spatial-temporal interactions among neighboring agents is at the heart of multi-agent problems such as motion forecasting and crowd navigation. Despite notable progress, it remains unclear to which extent modern representations can…

In the era of information overload, recommender systems (RSs) have become an indispensable part of online service platforms. Traditional RSs estimate user interests and predict their future behaviors by utilizing correlations in the…

Causal representation learning algorithms discover lower-dimensional representations of data that admit a decipherable interpretation of cause and effect; as achieving such interpretable representations is challenging, many causal learning…

Learning meaningful and compact representations with disentangled semantic aspects is considered to be of key importance in representation learning. Since real-world data is notoriously costly to collect, many recent state-of-the-art…

While human infants robustly discover their own causal efficacy, standard reinforcement learning agents remain brittle, as their reliance on correlation-based rewards fails in noisy, ecologically valid scenarios. To address this, we…

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Unsupervised semantic segmentation aims to achieve high-quality semantic grouping without human-labeled annotations. With the advent of self-supervised pre-training, various frameworks utilize the pre-trained features to train prediction…

Model interpretability plays a central role in human-AI decision-making systems. Ideally, explanations should be expressed using human-interpretable semantic concepts. Moreover, the causal relations between these concepts should be captured…

Medical diagnosis assistant (MDA) aims to build an interactive diagnostic agent to sequentially inquire about symptoms for discriminating diseases. However, since the dialogue records used to build a patient simulator are collected…

Explainable AI aims to render model behavior understandable by humans, which can be seen as an intermediate step in extracting causal relations from correlative patterns. Due to the high risk of possible fatal decisions in image-based…

User behavior data in recommender systems are driven by the complex interactions of many latent factors behind the users' decision making processes. The factors are highly entangled, and may range from high-level ones that govern user…

Concept-based explanations have emerged as a popular way of extracting human-interpretable representations from deep discriminative models. At the same time, the disentanglement learning literature has focused on extracting similar…

The real-world testing of decisions made using causal machine learning models is an essential prerequisite for their successful application. We focus on evaluating and improving contextual treatment assignment decisions: these are…

Accurately modeling users' evolving preferences from sequential interactions remains a central challenge in recommender systems. Recent studies emphasize the importance of capturing multiple latent intents underlying user behaviors.…

Recent breakthroughs in AI have shown the remarkable power of deep learning and deep reinforcement learning. These developments, however, have been tied to specific tasks, and progress in out-of-distribution generalization has been limited.…

One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequence of dynamic factors. To extract this latent information,…

Most of previous machine learning algorithms are proposed based on the i.i.d. hypothesis. However, this ideal assumption is often violated in real applications, where selection bias may arise between training and testing process. Moreover,…