FROG: Fair Removal on Graphs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912826699808768 |
|---|---|
| author | Chen, Ziheng Cheng, Jiali Amiri, Hadi Nag, Kaushiki Lin, Lu Liu, Sijia Sun, Xiangguo Tolomei, Gabriele |
| author_facet | Chen, Ziheng Cheng, Jiali Amiri, Hadi Nag, Kaushiki Lin, Lu Liu, Sijia Sun, Xiangguo Tolomei, Gabriele |
| contents | With growing emphasis on privacy regulations, machine unlearning has become increasingly critical in real-world applications such as social networks and recommender systems, many of which are naturally represented as graphs. However, existing graph unlearning methods often modify nodes or edges indiscriminately, overlooking their impact on fairness. For instance, forgetting links between users of different genders may inadvertently exacerbate group disparities. To address this issue, we propose a novel framework that jointly optimizes both the graph structure and the model to achieve fair unlearning. Our method rewires the graph by removing redundant edges that hinder forgetting while preserving fairness through targeted edge augmentation. We further introduce a worst-case evaluation mechanism to assess robustness under challenging scenarios. Experiments on real-world datasets show that our approach achieves more effective and fair unlearning than existing baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18197 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FROG: Fair Removal on Graphs Chen, Ziheng Cheng, Jiali Amiri, Hadi Nag, Kaushiki Lin, Lu Liu, Sijia Sun, Xiangguo Tolomei, Gabriele Machine Learning Artificial Intelligence With growing emphasis on privacy regulations, machine unlearning has become increasingly critical in real-world applications such as social networks and recommender systems, many of which are naturally represented as graphs. However, existing graph unlearning methods often modify nodes or edges indiscriminately, overlooking their impact on fairness. For instance, forgetting links between users of different genders may inadvertently exacerbate group disparities. To address this issue, we propose a novel framework that jointly optimizes both the graph structure and the model to achieve fair unlearning. Our method rewires the graph by removing redundant edges that hinder forgetting while preserving fairness through targeted edge augmentation. We further introduce a worst-case evaluation mechanism to assess robustness under challenging scenarios. Experiments on real-world datasets show that our approach achieves more effective and fair unlearning than existing baselines. |
| title | FROG: Fair Removal on Graphs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2503.18197 |