PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning.
FedRIR: Rethinking Information Representation in Federated Learning.
Maverick: Personalized Edge-Assisted Federated Learning with Contrastive Training.
NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on Adaptive Perturbation on Federated Graph Learning.
FLock: Robust and Privacy-Preserving Federated Learning based on Practical Blockchain State Channels.
Provably Robust Federated Reinforcement Learning.
Subgraph Federated Unlearning.
Federated Graph Anomaly Detection via Disentangled Representation Learning.
Personalized Federated Recommendation for Cold-Start Users via Adaptive Knowledge Fusion.
FedMobile: Enabling Knowledge Contribution-aware Multi-modal Federated Learning with Incomplete Modalities.
P4GCN: Vertical Federated Social Recommendation with Privacy-Preserving Two-Party Graph Convolution Network.
Aegis: Post-Training Attribute Unlearning in Federated Recommender Systems against Attribute Inference Attacks.
Empowering Federated Graph Rationale Learning with Latent Environments.
Dealing with Noisy Data in Federated Learning: An Incentive Mechanism with Flexible Pricing.
Horizontal Federated Heterogeneous Graph Learning: A Multi-Scale Adaptive Solution to Data Distribution Challenges.
MoCFL: Mobile Cluster Federated Learning Framework for Highly Dynamic Network.
Poisoning Attack on Federated Knowledge Graph Embedding.
Prompt-enhanced Federated Content Representation Learning for Cross-domain Recommendation.
Towards Energy-efficient Federated Learning via INT8-based Training on Mobile DSPs.
FedDSE: Distribution-aware Sub-model Extraction for Federated Learning over Resource-constrained Devices.
BlockDFL: A Blockchain-based Fully Decentralized Peer-to-Peer Federated Learning Framework.
Incentive and Dynamic Client Selection for Federated Unlearning.
Poisoning Federated Recommender Systems with Fake Users.
Accelerating the Decentralized Federated Learning via Manipulating Edges.
PAGE: Equilibrate Personalization and Generalization in Federated Learning.
Federated Learning Vulnerabilities: Privacy Attacks with Denoising Diffusion Probabilistic Models.
When Federated Recommendation Meets Cold-Start Problem: Separating Item Attributes and User Interactions.
How Few Davids Improve One Goliath: Federated Learning in Resource-Skewed Edge Computing Environments.
Privacy-Preserving and Fairness-Aware Federated Learning for Critical Infrastructure Protection and Resilience.
Co-clustering for Federated Recommender System.
Cardinality Counting in “Alcatraz”: A Privacy-aware Federated Learning Approach.
Towards Personalized Privacy: User-Governed Data Contribution for Federated Recommendation.
Federated Heterogeneous Graph Neural Network for Privacy-preserving Recommendation.
Towards Efficient Communication and Secure Federated Recommendation System via Low-rank Training.
Vertical Federated Knowledge Transfer via Representation Distillation for Healthcare Collaboration Networks.
Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding.
AgrEvader: Poisoning Membership Inference Against Byzantine-robust Federated Learning.
Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning.
Semi-decentralized Federated Ego Graph Learning for Recommendation.
Federated Node Classification over Graphs with Latent Link-type Heterogeneity.
FedEdge: Accelerating Edge-Assisted Federated Learning.
FlexiFed: Personalized Federated Learning for Edge Clients with Heterogeneous Model Architectures.
To Store or Not? Online Data Selection for Federated Learning with Limited Storage.
Interaction-level Membership Inference Attack Against Federated Recommender Systems.
FedACK: Federated Adversarial Contrastive Knowledge Distillation for Cross-Lingual and Cross-Model Social Bot Detection.
pFedPrompt: Learning Personalized Prompt for Vision-Language Models in Federated Learning.
Beyond Fine-Tuning: Efficient and Effective Fed-Tuning for Mobile/Web Users.
Federated Unlearning via Class-Discriminative Pruning.
An Accuracy-Lossless Perturbation Method for Defending Privacy Attacks in Federated Learning.
FedKC: Federated Knowledge Composition for Multilingual Natural Language Understanding.
Last updated 2 months ago