Full Description
The three-volume set LNICST 624, 625, 626 constitutes the refereed proceedings of the 20th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2024, held in Wuzhen, China, during November 14-17, 2024.
The 62 full papers were carefully reviewed and selected from 173 submissions. They are categorized under the topical sections as follows:
Edge computing & Task scheduling
Deep Learning and application
Blockchain applications
Security and Privacy Protection
Representation learning & Collaborative working
Graph neural networks & Recommendation systems
Federated Learning and application
Contents
Graph neural networks & Recommendation systems.- Time-aware Recommendations with Motif-Enhanced Graph Learning.- Spatial-Temporal Graph Attention Networks Based on Novel Adjacency Matrix For Weather Forecasting.- Repository-Level Code Generation Method Enhanced by Context-Dependent Graph Retrieval.- DGSR: Dual-Graph Sequential Recommendation with Gated and Heterogeneous GNNs.- Disentanglement-enhanced User Representation via Domain-level Clusters for Cross-Domain Recommendation.- Adaptive Web API Recommendation via Matching Service Clusters and Mashup Requirement.- Multi-channel Heterogeneous Graph Transformer based Unsupervised Anomaly Detection Model for IoT Time Series.- CBR-FIF: A Novel Dynamic Graph Node Embedding Computation Framework.- KG-ASI: A Knowledge Graph Enhanced Model-based Retriever for Document Retrieval.- Federated Learning and application.- Free-rider Attack Based on Data-free Knowledge Distillation in Federated Learning.- Client-Oriented Energy Optimization in Clustered Federated Learning with Model Partition.- FedUDA: Towards a Novel Unfairness Distribution Attack against Federated Learning Models.- Mal-GAT: A Method to Enhance Malware Traffic Detection with Graph Attention Networks.- A Federated Learning Framework with Blockchain and Cache Pools for Unreliable Devices in a Cloud-Edge-End Environment.- Model Similarity based Clustering Federated Learning in Edge Computing.- A Privacy-Preserving Edge Caching Algorithm Based on Permissioned Blockchain and Federated Reinforcement Learning.
