Related papers: Rina: Enhancing Ring-AllReduce with In-network Agg…

Machine learning models have achieved, and in some cases surpassed, human-level performance in various tasks, mainly through centralized training of static models and the use of large models stored in centralized clouds for inference.…

Reconfigurable distributed antenna and reflecting surface (RDARS) is a promising architecture for future sixth-generation (6G) wireless networks. In particular, the dynamic working mode configuration for the RDARS-aided system brings an…

Space-air-ground integrated network (SAGIN) is a new type of wireless network mode. The effective management of SAGIN resources is a prerequisite for high-reliability communication. However, the storage capacity of space-air network segment…

Deep Reinforcement Learning (RL) algorithms can solve complex sequential decision tasks successfully. However, they have a major drawback of having poor sample efficiency which can often be tackled by knowledge reuse. In Multi-Agent…

The increasing complexity of recent Wi-Fi amendments is making optimal Rate Adaptation (RA) a challenge. The use of classic algorithms or heuristic models to address RA is becoming unfeasible due to the large combination of configuration…

Reinforcement learning systems require good representations to work well. For decades practical success in reinforcement learning was limited to small domains. Deep reinforcement learning systems, on the other hand, are scalable, not…

AlphaGo's astonishing performance has ignited an explosive interest in developing deep reinforcement learning (DRL) for numerous real-world applications, such as intelligent robotics. However, the often prohibitive complexity of DRL stands…

Deep Reinforcement Learning (DRL) is vital in various AI applications. DRL algorithms comprise diverse compute kernels, which may not be simultaneously optimized using a homogeneous architecture. However, even with available heterogeneous…

Many engineering processes can be accurately modelled using partial differential equations (PDEs), but high dimensionality and non-convexity of the resulting systems pose limitations on their efficient optimisation. In this work, a model…

This study considers multiple reconfigurable intelligent surfaces (RISs)-aided multiuser downlink systems with the goal of jointly optimizing the transmitter precoding and RIS phase shift matrix to maximize spectrum efficiency. Unlike prior…

Integrated Access and Backhauling (IAB) is a viable approach for meeting the unprecedented need for higher data rates of future generations, acting as a cost-effective alternative to dense fiber-wired links. The design of such networks with…

Intrusion Detection Systems (IDS) play a crucial role in ensuring the security of computer networks. Machine learning has emerged as a popular approach for intrusion detection due to its ability to analyze and detect patterns in large…

Wide Area Networks (WAN) are a key infrastructure in today's society. During the last years, WANs have seen a considerable increase in network's traffic and network applications, imposing new requirements on existing network technologies…

The method of choice for parameter aggregation in Deep Neural Network (DNN) training, a network-intensive task, is shifting from the Parameter Server model to decentralized aggregation schemes (AllReduce) inspired by theoretical guarantees…

This paper studies how to improve the generalization performance and learning speed of the navigation agents trained with deep reinforcement learning (DRL). Although DRL exhibits huge potential in robot mapless navigation, DRL agents…

Deep learning (DL) based resource allocation (RA) has recently gained significant attention due to its performance efficiency. However, most related studies assume an ideal case where the number of users and their utility demands, e.g.,…

We develop a framework based on deep reinforce-ment learning (DRL) to solve the spectrum allocation problem inthe emerging integrated access and backhaul (IAB) architecturewith large scale deployment and dynamic environment. The avail-able…

The limited and dynamically varied resources on edge devices motivate us to deploy an optimized deep neural network that can adapt its sub-networks to fit in different resource constraints. However, existing works often build sub-networks…

In-network computing via smart networking devices is a recent trend for modern datacenter networks. State-of-the-art switches with near line rate computing and aggregation capabilities are developed to enable, e.g., acceleration and better…

We introduce latency-aware network acceleration (LANA) - an approach that builds on neural architecture search techniques and teacher-student distillation to accelerate neural networks. LANA consists of two phases: in the first phase, it…