mlsanityData to 7 Oct 2026

Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning

arXiv 2302.02069 ↗First posted 4 Feb 2023cs.LG cs.CLcited by 39

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Federated Learning (FL) recently emerges as a paradigm to train a global machine learning model across distributed clients without sharing raw data. Knowledge Graph (KG) embedding represents KGs in a continuous vector space, serving as the backbone of many knowledge-driven applications. As a promising combination, federated KG embedding can fully take advantage of knowledge learned from different clients while preserving the privacy of local data. However, realistic problems such as data heterogeneity and knowledge forgetting still remain to be concerned. In this paper, we propose FedLU, a novel FL framework for heterogeneous KG embedding learning and unlearning. To cope with the drift between local optimization and global convergence caused by data heterogeneity, we propose mutual knowledge distillation to transfer local knowledge to global, and absorb global knowledge back. Moreover, we present an unlearning method based on cognitive neuroscience, which combines retroactive interference and passive decay to erase specific knowledge from local clients and propagate to the global model by reusing knowledge distillation. We construct new datasets for assessing realistic performance of the state-of-the-arts. Extensive experiments show that FedLU achieves superior results in both link prediction and knowledge forgetting.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 29 of its 43 references that are in the map. First posted on arXiv 4 Feb 2023.

Builds on

29 of 43 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  5. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  6. 2019Machine Unlearningcited by 1,020
  7. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  8. 2016Complex Embeddings for Simple Link Predictioncited by 897
  9. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  10. 2021Model-Contrastive Federated Learningcited by 762
  11. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  12. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
17 more
  1. 2017Word Translation Without Parallel Datacited by 480
  2. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
  3. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  4. 2019Federated Machine Learning: Concept and Applicationscited by 409
  5. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 395
  6. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
  7. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
  8. 2019TuckER: Tensor Factorization for Knowledge Graph Completioncited by 290
  9. 2020Federated Learning of a Mixture of Global and Local Modelscited by 208
  10. 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 185
  11. 2020When Machine Unlearning Jeopardizes Privacycited by 181
  12. 2017A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Networkcited by 143
  13. 2019Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Predictioncited by 133
  14. 2020Federated Knowledge Distillationcited by 51
  15. 2020FedE: Embedding Knowledge Graphs in Federated Settingcited by 46
  16. 2021Differentially Private Federated Knowledge Graphs Embeddingcited by 45
  17. 2022Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregationcited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 14; 2025: 7; 2026: 8.

39 papers.

Sort:

By area:

  1. 2023Machine Unlearning: Solutions and Challengescited by 85
  2. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  3. 2023SAFE: Machine Unlearning With Shard Graphscited by 28
  4. 2024On Effects of Steering Latent Representation for Large Language Model Unlearningcited by 27
  5. 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metricscited by 25
  6. 2024Federated Distillation: A Surveycited by 14
  7. 2023Distill to Delete: Unlearning in Graph Networks with Knowledge Distillationcited by 13
  8. 2023FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learningcited by 12
  9. 2023A Survey of Graph Unlearningcited by 12
  10. 2024Trustworthy Federated Learning: Privacy, Security, and Beyondcited by 11
  11. 2024Machine Unlearning for Recommendation Systems: An Insightcited by 9
  12. 2025A Comprehensive Data-centric Overview of Federated Graph Learningcited by 7
27 more
  1. 2023Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generationcited by 6
  2. 2025TAPE: Tailored Posterior Difference for Auditing of Machine Unlearningcited by 6
  3. 2024Vertical Federated Unlearning via Backdoor Certificationcited by 4
  4. 2024Goldfish: An Efficient Federated Unlearning Frameworkcited by 3
  5. 2024Communication-Efficient Federated Knowledge Graph Embedding with Entity-Wise Top-K Sparsificationcited by 3
  6. 2025Unlearning for Federated Online Learning to Rank: A Reproducibility Studycited by 3
  7. 2025Efficient Knowledge Graph Unlearning with Zeroth-order Informationcited by 2
  8. 2026VL-KGE: Vision-Language Models Meet Knowledge Graph Embeddingscited by 2
  9. 2026FedV-KGQA: Multi-Hop Question Answering over Vertically Partitioned Knowledge Graphscited by 2
  10. 2023Exploring Federated Unlearning: Review, Comparison, and Insightscited by 1
  11. 2023FedMKGC: Privacy-Preserving Federated Multilingual Knowledge Graph Completioncited by 1
  12. 2024Federated Knowledge Graph Unlearning via Diffusion Modelcited by 1
  13. 2024Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillationcited by 1
  14. 2024Learn to Unlearn: Meta-Learning-Based Knowledge Graph Embedding Unlearningcited by 1
  15. 2025Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completioncited by 1
  16. 2025REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Featurecited by 1
  17. 2026Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglementcited by 1
  18. 2023Open Knowledge Base Canonicalization with Multi-task Unlearningcited by 0
  19. 2024A Survey on Federated Unlearning: Challenges and Opportunitiescited by 0
  20. 2024Beyond Right to be Forgotten: Managing Heterogeneity Side Effects Through Strategic Incentivescited by 0
  21. 2024Streamlined Federated Unlearning: Unite as One to Be Highly Efficientcited by 0
  22. 2025Federated Unlearning in the Wild: Rethinking Fairness and Data Discrepancycited by 0
  23. 2026FedUP: One-Shot Federated Unlearning via Centroid-Guided Plug-in Filterscited by 0
  24. 2026CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletioncited by 0
  25. 2026When Successful Knowledge Graph Edits Displace Correct Answers: Rank-Level Locality beyond Parameter Supportcited by 0
  26. 2026Cost Characterization of Vertically Partitioned Federated Knowledge Graphscited by 0
  27. 2026Federated Agent Optimizationcited by 0