相关论文: Information Bottleneck-Inspired Type Based Multipl…

In many applications, it is desirable to extract only the relevant aspects of data. A principled way to do this is the information bottleneck (IB) method, where one seeks a code that maximizes information about a 'relevance' variable, Y,…

In this letter, we propose a trellis-coded nonorthogonal multiple access (NOMA) scheme. The signals for different users are produced by trellis coded modulation (TCM) and then superimposed on different power levels. By interpreting the…

As a paradigm shift towards pervasive intelligence, semantic communication (SemCom) has shown great potentials to improve communication efficiency and provide user-centric services by delivering task-oriented semantic meanings. However, the…

By extracting task-relevant information while maximally compressing the input, the information bottleneck (IB) principle has provided a guideline for learning effective and robust representations of the target inference. However, extending…

The Information Bottleneck method is a learning technique that seeks a right balance between accuracy and generalization capability through a suitable tradeoff between compression complexity, measured by minimum description length, and…

In the context of statistical learning, the Information Bottleneck method seeks a right balance between accuracy and generalization capability through a suitable tradeoff between compression complexity, measured by minimum description…

The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks. Essentially, it aims to find a minimum sufficient representation $\mathbf{t}$ by striking a trade-off…

The information bottleneck (IB) method is a feasible defense solution against adversarial attacks in deep learning. However, this method suffers from the spurious correlation, which leads to the limitation of its further improvement of…

In this paper, we present an information-theoretic method for clustering mixed-type data, that is, data consisting of both continuous and categorical variables. The proposed approach extends the Information Bottleneck principle to…

Integrated learning and communication (ILAC) unifies learned transceivers with radio resource management, where semantic feature multiple access (SFMA) enables paired users to superpose their learned representations over shared…

Non-orthogonal multiple access (NOMA) has emerged as a novel air interface technology for massive connectivity in sixth-generation (6G) era. The recent integration of NOMA in backscatter communication (BC) has triggered significant research…

In Internet of Things (IoT) networks, the amount of data sensed by user devices may be huge, resulting in the serious network congestion. To solve this problem, intelligent data compression is critical. The variational information…

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…

Network-coded multiple access (NCMA) is a communication scheme for wireless multiple-access networks where physical-layer network coding (PNC) is employed. In NCMA, a user encodes and spreads its message into multiple packets. Time is…

The Information Bottleneck (IB) principle offers a compelling theoretical framework to understand how neural networks (NNs) learn. However, its practical utility has been constrained by unresolved theoretical ambiguities and significant…

Deep neural networks suffer from poor generalization to unseen environments when the underlying data distribution is different from that in the training set. By learning minimum sufficient representations from training data, the information…

Learning with hidden variables is a central challenge in probabilistic graphical models that has important implications for many real-life problems. The classical approach is using the Expectation Maximization (EM) algorithm. This…

Sparse code multiple access (SCMA) is a new frequency domain non-orthogonal multiple-access technique which can improve spectral efficiency of wireless radio access. With SCMA, different incoming data streams are directly mapped to…

In this research, we deal with the problem of visual question answering (VQA) in remote sensing. While remotely sensed images contain information significant for the task of identification and object detection, they pose a great challenge…

Desynchronization approaches in wireless sensor networks converge to time-division multiple access (TDMA) of the shared medium without requiring clock synchronization amongst the wireless sensors, or indeed the presence of a central…