Related papers: A new BAT for Acyclic Multistate Information Netwo…
With the fifth-generation (5G) mobile networks being actively standardized and deployed, many new vehicular communications technologies are developed to support and enrich various application scenarios. Unmanned aerial vehicle (UAV) enabled…
AI-generated content (AIGC) models, represented by large language models (LLM), have revolutionized content creation. High-speed next-generation communication technology is an ideal platform for providing powerful AIGC network services. At…
5G networks offer exceptional reliability and availability, ensuring consistent performance and user satisfaction. Yet they might still fail when confronted with the unexpected. A resilient system is able to adapt to real-world complexity,…
As transistor-based memory technologies like dynamic random access memory (DRAM) approach their scalability limits, the need to explore alternative storage solutions becomes increasingly urgent. Phase-change memory (PCM) has gained…
Neural networks are known to be vulnerable to adversarial attacks, which are small, imperceptible perturbations that can significantly alter the network's output. Conversely, there may exist large, meaningful perturbations that do not…
Stochastic gradient descent-based algorithms are widely used for training deep neural networks but often suffer from slow convergence. To address the challenge, we leverage the framework of the alternating direction method of multipliers…
This paper introduces the Univariate Gaussian Mixture Model Neural Network (uGMM-NN), a novel neural architecture that embeds probabilistic reasoning directly into the computational units of deep networks. Unlike traditional neurons, which…
Network robustness against attacks is one of the most fundamental researches in network science as it is closely associated with the reliability and functionality of various networking paradigms. However, despite the study on intrinsic…
Many applications in machine learning can be framed as minimization problems and solved efficiently using gradient-based techniques. However, recent applications of generative models, particularly GANs, have triggered interest in solving…
Recent advancements in physics-informed neural networks (PINNs) and their variants have garnered substantial focus from researchers due to their effectiveness in solving both forward and inverse problems governed by differential equations.…
Neural networks (NNs) can achieved high performance in various fields such as computer vision, and natural language processing. However, deploying NNs in resource-constrained safety-critical systems has challenges due to uncertainty in the…
Increasing penetration of inverter-based resources, flexible loads, and rapidly changing operating conditions make higher-order $N\!-\!k$ contingency assessment increasingly important but computationally prohibitive. Exhaustive evaluation…
Verification of binary neural network (BNN) robustness is NP-hard, as it can be formulated as a combinatorial search for an adversarial perturbation that induces misclassification. Exact verification methods therefore scale poorly with…
5G and Beyond networks promise low-latency support for applications that need to deliver mission-critical data with strict deadlines. However, innovations on the physical and medium access layers are not sufficient. Additional…
Influence maximization (IM) seeks to identify a seed set that maximizes influence within a network, with applications in areas such as viral marketing, disease control, and political campaigns. The budgeted influence maximization (BIM)…
The diversity of fifth generation (5G) network use cases, multiple access technologies, and network deployments requires measures of network robustness that complement throughput-centric error rates. In this paper, we investigate robustness…
BATS (BATched Sparse) codes are a class of efficient random linear network coding variation that has been studied for multihop wireless networks mostly in scenarios of a single communication flow. Towards sophisticated multi-flow network…
A consistency/latency tradeoff arises as soon as a distributed storage system replicates data. For low latency, modern storage systems often settle for weak consistency conditions, which provide little, or even worse, no guarantee for data…
We have witnessed the discovery of many techniques for network representation learning in recent years, ranging from encoding the context in random walks to embedding the lower order connections, to finding latent space representations with…
We expand a set of notions recently introduced providing the general setting for a universal representation of the quantum structure on which quantum information stands. The dynamical evolution process associated with generic quantum…