Related papers: Universal Physiological Representation Learning wi…
The gap between sensing patterns of different face modalities remains a challenging problem in heterogeneous face recognition (HFR). This paper proposes an adversarial discriminative feature learning framework to close the sensing gap via…
Given a dataset of images containing different objects with different features such as shape, size, rotation, and x-y position; and a Variational Autoencoder (VAE); creating a disentangled encoding of these features in the hidden space…
Recommendation models are typically trained on observational user interaction data, but the interactions between latent factors in users' decision-making processes lead to complex and entangled data. Disentangling these latent factors to…
Complex categorical data is often hierarchically coupled with heterogeneous relationships between attributes and attribute values and the couplings between objects. Such value-to-object couplings are heterogeneous with complementary and…
Disentangled representation learning has undoubtedly benefited from objective function surgery. However, a delicate balancing act of tuning is still required in order to trade off reconstruction fidelity versus disentanglement. Building on…
Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are interested in learning…
Paradoxically, a Variational Autoencoder (VAE) could be pushed in two opposite directions, utilizing powerful decoder model for generating realistic images but collapsing the learned representation, or increasing regularization coefficient…
Disentangled learning representations have promising utility in many applications, but they currently suffer from serious reliability issues. We present Gaussian Channel Autoencoder (GCAE), a method which achieves reliable disentanglement…
Goal-conditioned reinforcement learning is a crucial yet challenging algorithm which enables agents to achieve multiple user-specified goals when learning a set of skills in a dynamic environment. However, it typically requires millions of…
Building universal user representations that capture the essential aspects of user behavior is a crucial task for modern machine learning systems. In real-world applications, a user's historical interactions often serve as the foundation…
An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), for instance, strongly relies on this…
A variational autoencoder (VAE) is a probabilistic machine learning framework for posterior inference that projects an input set of high-dimensional data to a lower-dimensional, latent space. The latent space learned with a VAE offers…
The increasing availability of electrocardiogram (ECG) data has motivated the use of data-driven models for automating various clinical tasks based on ECG data. The development of subject-specific models are limited by the cost and…
In recent years, the field of machine learning has made phenomenal progress in the pursuit of simulating real-world data generation processes. One notable example of such success is the variational autoencoder (VAE). In this work, with a…
An alternative pathway for the human brain to communicate with the outside world is by means of a brain computer interface (BCI). A BCI can decode electroencephalogram (EEG) signals of brain activities, and then send a command or an intent…
Autoencoders (AE) have recently been widely employed to approach the novelty detection problem. Trained only on the normal data, the AE is expected to reconstruct the normal data effectively while fail to regenerate the anomalous data,…
In classification problems, supervised machine-learning methods outperform traditional algorithms, thanks to the ability of neural networks to learn complex patterns. However, in two-class classification tasks like anomaly or fraud…
We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm…
The variational autoencoder (VAE) is a simple and efficient generative artificial intelligence method for modeling complex probability distributions of various types of data, such as images and texts. However, it suffers some main…
The claims data, containing medical codes, services information, and incurred expenditure, can be a good resource for estimating an individual's health condition and medical risk level. In this study, we developed Transformer-based…