Related papers: Tackling Distribution Shifts in Task-Oriented Comm…
Despite its notable success in adversarial learning approaches to multi-domain task-oriented dialog system, training the dialog policy via adversarial inverse reinforcement learning often fails to balance the performance of the policy…
Speaker diarization is an important problem that is topical, and is especially useful as a preprocessor for conversational speech related applications. The objective of this paper is two-fold: (i) segment initialization by uniformly…
The emergence of Graph Convolutional Network (GCN) has greatly boosted the progress of graph learning. However, two disturbing factors, noise and redundancy in graph data, and lack of interpretation for prediction results, impede further…
While large-scale pretrained language models have obtained impressive results when fine-tuned on a wide variety of tasks, they still often suffer from overfitting in low-resource scenarios. Since such models are general-purpose feature…
In the realm of neural network models, the perpetual challenge remains in retaining task-relevant information while effectively discarding redundant data during propagation. In this paper, we introduce IB-AdCSCNet, a deep learning model…
Emerging diseases present challenges in symptom recognition and timely clinical intervention due to limited available information. An effective prognostic model could assist physicians in making accurate diagnoses and designing personalized…
Integration of data from multiple omics techniques is becoming increasingly important in biomedical research. Due to non-uniformity and technical limitations in omics platforms, such integrative analyses on multiple omics, which we refer to…
We propose a novel unsupervised framework for \emph{Invariant Risk Minimization} (IRM), extending the concept of invariance to settings where labels are unavailable. Traditional IRM methods rely on labeled data to learn representations that…
Collaborative edge sensing systems, particularly in collaborative perception systems in autonomous driving, can significantly enhance tracking accuracy and reduce blind spots with multi-view sensing capabilities. However, their limited…
Information bottleneck (IB) is a method for extracting information from one random variable $X$ that is relevant for predicting another random variable $Y$. To do so, IB identifies an intermediate "bottleneck" variable $T$ that has low…
In task-oriented semantic communications, the transmitters are designed to deliver task-related semantic information rather than every signal bit to receivers, which alleviates the spectrum pressure by reducing network traffic loads.…
Information bottleneck (IB) principle [1] has become an important element in information-theoretic analysis of deep models. Many state-of-the-art generative models of both Variational Autoencoder (VAE) [2; 3] and Generative Adversarial…
Goal-oriented semantic communication (SC) aims to revolutionize communication systems by transmitting only task-essential information. However, current approaches face challenges such as joint training at transceivers, leading to redundant…
Generative diversity varies significantly across discrete latent generative models such as AR, MIM, and Diffusion. We propose a diagnostic framework, grounded in Information Bottleneck (IB) theory, to analyze the underlying strategies…
The information bottleneck (IB) principle has been suggested as a way to analyze deep neural networks. The learning dynamics are studied by inspecting the mutual information (MI) between the hidden layers and the input and output. Notably,…
Domain generalization models learn to generalize to previously unseen domains, but suffer from prediction uncertainty and domain shift. In this paper, we address both problems. We introduce a probabilistic meta-learning model for domain…
Information Bottleneck (IB) is a widely used framework that enables the extraction of information related to a target random variable from a source random variable. In the objective function, IB controls the trade-off between data…
Deep learning representations are often difficult to interpret, which can hinder their deployment in sensitive applications. Concept Bottleneck Models (CBMs) have emerged as a promising approach to mitigate this issue by learning…
Intelligent task-oriented semantic communications~(SemComs) have witnessed great progress with the development of deep learning~(DL), where multi-task SemComs that perform multiple tasks simultaneously attach great importance due to its…
Unified multimodal large language models (MLLMs) aim to unify image understanding and image generation within a single framework, where a shared visual tokenizer serves as the sole interface that maps high-dimensional images into a limited…