Related papers: Information Bottleneck-Inspired Type Based Multipl…

We consider the detection of correlated information sources in the ubiquitous Code-Division Multiple-Access (CDMA) scheme. We propose a message-passing based scheme for detecting correlated sources directly, with no need for source coding.…

Invariant risk minimization (IRM) has recently emerged as a promising alternative for domain generalization. Nevertheless, the loss function is difficult to optimize for nonlinear classifiers and the original optimization objective could…

Semantic communication is a new paradigm that exploits deep learning models to enable end-to-end communications processes, and recent studies have shown that it can achieve better noise resiliency compared with traditional communication…

Non-orthogonal multiple access (NoMA) as an efficient way of radio resource sharing can root back to the network information theory. For generations of wireless communication systems design, orthogonal multiple access (OMA) schemes in time,…

This article introduces a novel communication paradigm for the unsourced, uncoordinated Gaussian multiple access problem. The major components of the envisioned framework are as follows. The encoded bits of every message are partitioned…

This paper describes a novel design of a neural network-based speech generation model for learning prosodic representation.The problem of representation learning is formulated according to the information bottleneck (IB) principle. A…

With the ever-increasing user density and quality of service (QoS) demand,5G networks with limited spectrum resources are facing massive access challenges. To address these challenges, in this paper, we propose a novel discrete semantic…

Next-generation wireless networks are projected to empower a broad range of Internet-of-things (IoT) applications and services with extreme data rates, posing new challenges in delivering large-scale connectivity at a low cost to current…

Information Bottleneck (IB) is widely used, but in deep learning, it is usually implemented through tractable surrogates, such as variational bounds or neural mutual information (MI) estimators, rather than directly controlling the MI…

Learning invariant (causal) features for out-of-distribution (OOD) generalization has attracted extensive attention recently, and among the proposals invariant risk minimization (IRM) is a notable solution. In spite of its theoretical…

Adapting decoder-only multimodal large language models (MLLMs) for unified multimodal retrieval faces two structural gaps. First, existing methods rely on implicit pooling, which overloads the hidden state of a standard vocabulary token…

Machine-to-machine (M2M) constitutes the communication paradigm at the basis of Internet of Things (IoT) vision. M2M solutions allow billions of multi-role devices to communicate with each other or with the underlying data transport…

Sparse code multiple access (SCMA), as a codebook-based non-orthogonal multiple access (NOMA) technique, has received research attention in recent years. The codebook design problem for SCMA has also been studied to some extent since…

We investigate the fundamental multiple access (MA) scheme in an active intelligent reflecting surface (IRS) aided energy-constrained Internet-of-Things (IoT) system, where an active IRS is deployed to assist the uplink transmission from…

One of the primary objectives for future wireless communication networks is to facilitate the provision of ultra-reliable and low-latency communication services while simultaneously ensuring the capability for vast connection. In order to…

We describe a new synchronous and distributed medium access control (MAC) protocol for multihop wireless networks that provides bandwidth guarantees to unicast connections. Our MAC protocol is based on a slotted time division multiple…

In classical information theory, the information bottleneck method (IBM) can be regarded as a method of lossy data compression which focusses on preserving meaningful (or relevant) information. As such it has recently gained a lot of…

This paper considers joint beamformer design towards maximizing the mutual information in a coherent wireless sensor network with noisy observation and multiple antennae. Leveraging the weighted minimum mean square error and block…

Gradient-based explanation methods are increasingly used to interpret neural models in natural language processing (NLP) due to their high fidelity. Such methods determine word-level importance using dimension-level gradient values through…

Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability. To address this, we propose Text Bottleneck Models (TBM), an intrinsically…