Database Paper Browser

Back to papers

Communication Efficient and Provable Federated Unlearning

Summary: Proposes FATS, a TV-stable FedAvg variant that enables communication-efficient, provable exact federated unlearning by making the unlearned model statistically indistinguishable from retraining without the deleted data. Provides client- and sample-level unlearning algorithms with convergence/unlearning guarantees and empirical gains on 6 benchmarks. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13361
Venue
VLDB
Year
2024
Pagerank
-
Overall Rank
13,151 | 8.52%
DOI
10.14778/3641204.3641220

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 0 of 0 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Semantically Similar Papers