Multi-agent active search requires autonomous agents to choose sensing actions that efficiently locate targets. In a realistic setting, agents also must consider the costs that their decisions incur. Previously proposed active search algorithms simplify the problem by ignoring uncertainty in the agent's environment, using myopic decision making, and/or overlooking costs. In this paper, we introduce an online active search algorithm to detect targets in an unknown environment by making adaptive cost-aware decisions regarding the agent's actions. Our algorithm combines principles from Thompson Sampling (for search space exploration and decentralized multi-agent decision making), Monte Carlo Tree Search (for long horizon planning) and pareto-optimal confidence bounds (for multi-objective optimization in an unknown environment) to propose an online lookahead planner that removes all the simplifications. We analyze the algorithm's performance in simulation to show its efficacy in cost aware active search.
Mobility-Aware Asynchronous Federated Learning with Dynamic Sparsification
Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University（北京信息科学与技术国家研究中心，电子工程系，清华大学）；School of Electronic and Information Engineering, Beijing Jiaotong University（电子与信息工程学院，北京交通大学）
Time-aware Dynamic Graph Embedding for Asynchronous Structural Evolution
The Hong Kong Polytechnic University（香港理工大学）；The University of Queensland（昆士兰大学）；The Griffith University（格里菲斯大学）；The Hong Kong University of Science and Technology（香港科技大学）
针对动态图局部结构异步演化被忽视的问题，本文将其建模为含 ToV 与 ToE 的时序边序列，并提出时间感知 Transformer 嵌入动态连接及时长，在多类图挖掘任务上优于现有方法且高效可扩展。
Asynchronous Risk-Aware Multi-Agent Packet Routing for Ultra-Dense LEO Satellite Networks
The Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg（安全、可靠性与信任跨学科研究中心（SnT），卢森堡大学）；School of Computer Sciense and Cyber Engineering, Guangzhou University（计算机科学与网络工程学院，广州大学）
FedSA-GCL: A Semi-Asynchronous Federated Graph Learning Framework with Personalized Aggregation and Cluster-Aware Broadcasting
Shandong University, School of Airspace Science（山东大学，空天科学学院）；Beijing Institute of Technology, School of Computer Science（北京理工大学，计算机科学学院）；Sun Yat-sen University, School of Computer Science（中山大学，计算机科学学院）
Asynchronous Parallel Incremental Block-Coordinate Descent for Decentralized Machine Learning
Royal Institute of Technology (KTH)（瑞典皇家理工学院）
机器学习（Machine Learning，ML）是大数据驱动的大规模物联网（Internet of Things，IoT）智能普适计算建模与分析的关键技术。对于快速增长的应用程序和数据量，分布式学习是一个有前途的新兴范式，因为它通常是不切实际的或效率低下的共享/聚合数据到一个集中的位置从不同的。本文研究了在分散式系统上训练ML模型的问题，其中数据分布在许多用户设备上，学习算法在设备上运行，目的是减轻中央实体/服务器的负担。虽然基于流言的方法已经在不同的用例中用于此目的，但它们遭受高通信成本，特别是当设备数量很大时。为了缓解这一问题，提出了基于增量的方法。我们首先为去中心化ML引入增量块坐标下降（I-BCD），它可以以运行时间为代价降低通信成本。为了加快收敛速度，提出了一种异步并行增量BCD（API-BCD）方法，其中多个设备/代理以异步方式活动。我们推导出所提出的方法的收敛性。仿真结果还表明，我们的API-BCD方法在运行时间和通信成本方面优于现有技术。
FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices using a Computing Power Aware Scheduler
Argonne National Laboratory（阿贡国家实验室）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；VMWare Research（威睿研究院）；The University of Chicago（芝加哥大学）
AP-BMM: Approximating Capability-Cost Pareto Sets of LLMs via Asynchronous Prior-Guided Bayesian Model Merging
Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies（广东新型安全智能技术重点实验室）；Institute of Cyberspace Security（网络空间安全研究院）；School of Computer Science and Technology（计算机科学与技术学院）
AsyncCouple-Flow: Asynchronous Cross-Modal Coupling and Flow Matching for Spatio-Temporal Forecasting
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Emory University（埃默里大学）；University of California, Berkeley（加州大学伯克利分校）；Yale University（耶鲁大学）；Stevens Institute of Technology（史蒂文斯理工学院）；City University of New York（纽约城市大学）
