# MMFGU: Multimodal Federated Graph Unlearning

arXiv: https://arxiv.org/abs/2607.28708 · HTML: https://mlsanity.com/paper/2607.28708/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Placed in Graph unlearning, one of 12 directions in LLM safety and security.
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Placed in

- LLM safety and security / [Graph unlearning](https://mlsanity.com/safety/graph-unlearning/)

## Builds on (most cited first, 22 of 22)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Adaptive Universal Generalized PageRank Graph Neural Network](https://mlsanity.com/paper/2006.07988/) (2020)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Deep Learning on Graphs: A Survey](https://mlsanity.com/paper/1812.04202/) (2018)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [RedCaps: web-curated image-text data created by the people, for the people](https://mlsanity.com/paper/2111.11431/) (2021)
- [Subgraph Federated Learning with Missing Neighbor Generation](https://mlsanity.com/paper/2106.13430/) (2021)
- [Fine-Grained Spoiler Detection from Large-Scale Review Corpora](https://mlsanity.com/paper/1905.13416/) (2019)
- [NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendation](https://mlsanity.com/paper/2309.07705/) (2023)
- [Federated Unlearning with Gradient Descent and Conflict Mitigation](https://mlsanity.com/paper/2412.20200/) (2024)
- [Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement](https://mlsanity.com/paper/2505.12684/) (2025)
- [MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learning](https://mlsanity.com/paper/2601.22416/) (2026)
- [OpenMAG: A Comprehensive Benchmark for Multimodal-Attributed Graph](https://mlsanity.com/paper/2602.05576/) (2026)
- [FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling](https://mlsanity.com/paper/2510.07755/) (2025)
- [A Comprehensive Data-centric Overview of Federated Graph Learning](https://mlsanity.com/paper/2507.16541/) (2025)

## Abstract (arXiv)

Multimodal federated graph learning enables clients to collaboratively train graph models over structural, textual, and visual signals without sharing private local data. However, the presence of heterogeneous multimodal content also makes unlearning requests more frequent and fine-grained: users may delete accounts or interactions, remove a particular image or text while retaining the associated entity, or revoke the learned correspondence between retained modalities or graph attributes. Existing federated graph unlearning mainly handles entity/relation or client removal and cannot directly satisfy these multimodal requests. They introduce three challenges: removing only the requested information without damaging retained content, preventing the target from being recovered through remaining modalities or graph neighborhoods, and stopping related traces on other clients from re-entering the global model after aggregation. To address them, we propose textscMMFGU, a multimodal federated graph unlearning framework built around target-specific representation decoupling. textscMMFGU maps heterogeneous requests into unified target carriers, decouples requested representations while anchoring retained semantics, exposes and repairs propagated residuals with lightweight probes, and selectively purges affected clients through compact prototype and response signals. Experiments show that textscMMFGU effectively removes requested information, preserves retained graph utility, and achieves a boldsymbol41.5× speedup over full retraining.