Related papers: Twin Auto-Encoder Model for Learning Separable Rep…
Effective representation learning is critical for short text clustering due to the sparse, high-dimensional and noise attributes of short text corpus. Existing pre-trained models (e.g., Word2vec and BERT) have greatly improved the…
Deep learning models are increasingly deployed in real-world applications. These models are often deployed on the server-side and receive user data in an information-rich representation to solve a specific task, such as image…
In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria. Our experiments show that…
The rapid development of deep-learning enabled task-oriented communications (TOC) significantly shifts the paradigm of wireless communications. However, the high computation demands, particularly in resource-constrained systems e.g., mobile…
Deep generative models applied to audio have improved by a large margin the state-of-the-art in many speech and music related tasks. However, as raw waveform modelling remains an inherently difficult task, audio generative models are either…
While the beta-VAE family is aiming to find disentangled representations and acquire human-interpretable generative factors, like what an ICA (from the linear domain) does, we propose Full Encoder, a novel unified autoencoder framework as a…
The successes achieved by deep neural networks in computer vision tasks have led in recent years to the emergence of a new research area dubbed Multi-Dimensional Encoding (MDE). Methods belonging to this family aim to transform tabular data…
Even though BERT achieves successful performance improvements in various supervised learning tasks, applying BERT for unsupervised tasks still holds a limitation that it requires repetitive inference for computing contextual language…
This paper presents TCE: Temporally Coherent Embeddings for self-supervised video representation learning. The proposed method exploits inherent structure of unlabeled video data to explicitly enforce temporal coherency in the embedding…
Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the…
The choice of an appropriate bottleneck dimension and the application of effective regularization are both essential for Autoencoders to learn meaningful representations from unlabeled data. In this paper, we introduce a new class of…
In the training of deep learning models, how the model parameters are initialized greatly affects the model performance, sample efficiency, and convergence speed. Representation learning for model initialization has recently been actively…
Variational Autoencoders (VAEs) are powerful in data representation inference, but it cannot learn relations between features with its vanilla form and common variations. The ability to capture relations within data can provide the much…
Masked Autoencoders is a simple yet powerful self-supervised learning method. However, it learns representations indirectly by reconstructing masked input patches. Several methods learn representations directly by predicting representations…
We propose an algorithm, guided variational autoencoder (Guided-VAE), that is able to learn a controllable generative model by performing latent representation disentanglement learning. The learning objective is achieved by providing…
Detecting rare and diverse anomalies in highly imbalanced datasets-such as Advanced Persistent Threats (APTs) in cybersecurity-remains a fundamental challenge for machine learning systems. Active learning offers a promising direction by…
Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only…
Blind image quality assessment (BIQA) is a challenging problem with important real-world applications. Recent efforts attempting to exploit powerful representations by deep neural networks (DNN) are hindered by the lack of subjectively…
Zero-shot Learning (ZSL) classification categorizes or predicts classes (labels) that are not included in the training set (unseen classes). Recent works proposed different semantic autoencoder (SAE) models where the encoder embeds a visual…
Advanced Persistent Threats (APTs) present a considerable challenge to cybersecurity due to their stealthy, long-duration nature. Traditional supervised learning methods typically require large amounts of labeled data, which is often scarce…