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.

Learning-Augmented Size-Based Job Scheduling 1
Programmable Physical Layers for Flexible Wireless Networks 1
Mitigating Expert Collapse in Sparse Mixture of Experts 1
Erasure Coding for Fault Tolerant Distributed Systems 1
Mitigating Cold Start Latency in Serverless Computing 1
Overcoming Data Scarcity in Wireless Machine Learning 1
Spatial Point Processes for Wireless Network Analysis 1
Fair Resource Allocation via Proportional Sharing 1
Mitigating the All-to-All Communication Bottleneck in Distributed MoEs 1
Optimizing Data Locality for Non-Uniform Memory Access 1
Accounting for Node Heterogeneity in Distributed Networks 1
Information Theory for Short Packet Wireless Communications 1
Amortizing Cryptographic Verification Costs 1
Latent Environment Discovery for Invariant Learning 1
Semantic Search via Dense Vector Retrieval 1

Top Authors

AuthorPapers
Haiming Jin4
Ben Liang3
Xiaojun Lin3
Atilla Eryilmaz2
Dian Shen2
Fan Dang2
Fangming Liu2
Fu Xiao2
Gaogang Xie2
George Iosifidis2
Huadong Ma2
Jianping Wang2
John C.S. Lui2
Lei Yang2
Liekang Zeng2
Lingjie Duan2
Linke Guo2
Long Chen2
Min Dong2
Ness Shroff2

Impactful Papers

Papers from INFOCOM 2025 that shaped research clusters.

Influential

Papers

Title
mmWave-Based Relay Reflector Reconstruction for LiDAR-Free Around-Corner Human Sensing
MUFFLER: Secure Tor Traffic Obfuscation with Dynamic Connection Shuffling and Splitting
MULoc: Towards Millimeter-Accurate Localization for Unlimited UWB Tags via Anchor Overhearing
Multi-Tier Multi-Node Scheduling of LLM for Collaborative AI Computing
Network CoPilot: Intent-Driven Network Configuration Updating for Service Guarantee
Network Diffuser for Placing-Scheduling Service Function Chains with Inverse Demonstration
NovaPlan: An Efficient Plan of Renting Ground Stations for Emerging LEO Satellite Networks
Novel Drift-Based Design and Analysis for Synchronized and Fresh Communication over Broadcast Channels
One Snapshot is All You Need: A Generalized Method for mmWave Signal Generation
Online Context Caching for Distributed Large Language Models Serving
On the Low-Complexity of Fair Learning for Combinatorial Multi-Armed Bandit
OPTICS: Human Activity-Aware Integrated Optical Wireless Communication and Sensing
Optimal and Approximate Parallelism-Based Computation Offloading Algorithms for Real-Time Multimodal Learning at the Edge
Optimal Real-Time Synchronized Scheduling for Collaborative Content Delivery
Optimizing Distributed Deployment of Mixture-of-Experts Model Inference in Serverless Computing
Oracle: QoS-Aware Online Service Provisioning in Non-Terrestrial Networks with Safe Transfer Learning
Partially Synchronous BFT Consensus Made Practical in Wireless Networks
PhaseMO: A Universal Massive MIMO Architecture for Sustainable NextG
PhyDNNs: Bringing Deep Neural Networks to the Physical Layer
Prediction-Assisted Online Distributed Deep Learning Workload Scheduling in GPU Clusters
Prism: Mining Task-aware Domains in Non-i.i.d. IMU Data for Flexible User Perception
Privacy-Preserving Wi-Fi Data Generation via Differential Privacy in Diffusion Models
Protocol-Agnostic and Data-Free Backdoor Attacks on Pre-Trained Models in RF Fingerprinting
PSFL: Parallel-Sequential Federated Learning with Convergence Guarantees
QLLMS: Quantization-Adaptive LLM Scheduling for Partially Informed Edge Serving Systems
Quark: Implementing Convolutional Neural Networks Entirely on Programmable Data Plane
Repurposing Optical Mice for Acoustic Eavesdropping
RFNOID: Protecting RFID Motion Privacy via Metasurface
Ricochet: Scalable Passive Beamforming for mmWave Networks Using Reflectarrays
Robust Contextual Combinatorial Multi-Armed Bandits for Unreliable Network Systems
SAIP: Accurate Detection of Anycast Servers with the Rise of Regional Anycast
SatPipe: Deterministic TCP Adaptation for Highly Dynamic LEO Satellite Networks
Scaling Learning-based Packet Classification Hardware with NeuTree
Secure Device Authentication for MmWave MIMO Systems via Mutual Coupling and Spatial AoA
SenFEED: Dynamic Decentralized Oracle Services for Accurate and Real-Time Sensor Data
SentinelX: A Lightweight Malicious Traffic Detection System Based on Programmable Switches
Similarity-Guided Rapid Deployment of Federated Intelligence Over Heterogeneous Edge Computing
Smooth Handovers via Smoothed Online Learning
SP-MoE: Expediting Mixture-of-Experts Training with Optimized Pipelining Planning
SweaTag: Fine-Grained Sweat Amount Sensing with COTS RFID Tags
Swing Filter: A Low-Overhead Filter with Larger Filtering Range for Network Traffic Measurement
Symmetry-Preserving Architecture for Multi-NUMA Environments (SPANE): A Deep Reinforcement Learning Approach for Dynamic VM Scheduling
Theory of Mixture-of-Experts for Mobile Edge Computing
The Power of Two in Large Service-Marketplaces
Towards Federated Inference: An Online Model Ensemble Framework for Cooperative Edge AI
Towards Guaranteed Accuracy for Flow Spread Measurement with $(\epsilon, \beta)$-Nonduplicate Sampling
Towards Lightweight Traffic Forecasting in RDMA Networks: Design and Application
Tri-Ring: Asynchronous Service Provisioning with Online Learning in Edge Cloud Networks
TurboCache: Empowering Switch-Accelerated Key-Value Caches with Accurate and Fast Cache Updates
Understanding the Business of Online Affiliate Marketing: An Empirical Study

« prev Page 3/4 next »