INFOCOM 2025
157 papers
INFOCOM 2025 featured 135 papers focusing on the intersection of networking and advanced machine learning. A central theme of the research involved addressing challenges in machine learning beyond the independent and identically distributed (IID) assumption. This included developing formal metrics for data heterogeneity in federated learning, latent environment inference for invariant learning, and methods for determining the number of components in latent mixture models.
The conference also highlighted diverse applications in wireless communication and security. Research included wireless radiation field reconstruction using 3D Gaussian splatting, sustainable massive MIMO architectures, and the repurposing of optical mice for acoustic eavesdropping. Other studies examined cost-effective storage for permissionless blockchains and contextual bandit learning in mobile crowdsourcing. Prolific contributors to this year's proceedings included Haiming Jin, Tony Q. S. Quek, Zhichao Cao, and Jun Luo, alongside researchers such as Yulong Shen, Fu Xiao, and Weiping Wang.
Top Research Directions
Research directions most represented by INFOCOM 2025 papers.
Top Authors
Impactful Papers
Papers from INFOCOM 2025 that shaped research clusters.
Influential
Optimizing Distributed Deployment of Mixture-of-Experts Model Inference in Serverless Computing
influential
Mitigating Expert Collapse in Sparse Mix
CARE: Compatibility-Aware Incentive Mechanisms for Federated Learning with Budgeted Requesters
influential
Federated Learning with Intermittent and