相关论文: Learning Disentangled Representation by Exploiting…

We propose TopDis (Topological Disentanglement), a method for learning disentangled representations via adding a multi-scale topological loss term. Disentanglement is a crucial property of data representations substantial for the…

Learning disentangled causal representations is a challenging problem that has gained significant attention recently due to its implications for extracting meaningful information for downstream tasks. In this work, we define a new notion of…

This paper tackles the problem of disentangling the latent variables of style and content in language models. We propose a simple yet effective approach, which incorporates auxiliary multi-task and adversarial objectives, for label…

The advancements in disentangled representation learning significantly enhance the accuracy of counterfactual predictions by granting precise control over instrumental variables, confounders, and adjustable variables. An appealing method…

Disentanglement, a critical concern in interpretable machine learning, has also garnered significant attention from the computer vision community. Many existing GAN-based class disentanglement (unsupervised) approaches, such as InfoGAN and…

Representations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a multitude of downstream tasks. In this paper we explore whether it is possible to…

Differentiable rendering has paved the way to training neural networks to perform "inverse graphics" tasks such as predicting 3D geometry from monocular photographs. To train high performing models, most of the current approaches rely on…

Recent research has made the surprising finding that state-of-the-art deep learning models sometimes fail to generalize to small variations of the input. Adversarial training has been shown to be an effective approach to overcome this…

Humans have a remarkable ability to disentangle complex sensory inputs (e.g., image, text) into simple factors of variation (e.g., shape, color) without much supervision. This ability has inspired many works that attempt to solve the…

Unsupervised representation learning has recently received lots of interest due to its powerful generalizability through effectively leveraging large-scale unlabeled data. There are two prevalent approaches for this, contrastive learning…

We propose a framework to analyze how multivariate representations disentangle ground-truth generative factors. A quantitative analysis of disentanglement has been based on metrics designed to compare how one variable explains each…

Disentangling factors of variation within data has become a very challenging problem for image generation tasks. Current frameworks for training a Generative Adversarial Network (GAN), learn to disentangle the representations of the data in…

Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, $\textit{i.e.,}$ RL agents suffer from low sample efficiency in environments with variations. While various approaches have attempted to…

Deep neural networks are susceptible to learn biased models with entangled feature representations, which may lead to subpar performances on various downstream tasks. This is particularly true for under-represented classes, where a lack of…

Disentangled representations can be useful in many downstream tasks, help to make deep learning models more interpretable, and allow for control over features of synthetically generated images that can be useful in training other models…

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…

Learning disentangled representations is a key step towards effectively discovering and modelling the underlying structure of environments. In the natural sciences, physics has found great success by describing the universe in terms of…

Learning representations that disentangle the underlying factors of variability in data is an intuitive way to achieve generalization in deep models. In this work, we address the scenario where generative factors present a multimodal…

Confounding bias is a crucial problem when applying machine learning to practice, especially in clinical practice. We consider the problem of learning representations independent to multiple biases. In literature, this is mostly solved by…

Social recommendations utilize social relations to enhance the representation learning for recommendations. Most social recommendation models unify user representations for the user-item interactions (collaborative domain) and social…