Efficient Model Updates for Approximate Unlearning of Graph-Structured Data

Authors: Eli Chien, Chao Pan, Olgica Milenkovic

ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical evaluations of six benchmark datasets demonstrate excellent performance/complexity/privacy trade-offs of our approach compared to complete retraining and general methods that do not leverage graph information.
Researcher Affiliation Academia Eli Chien Chao Pan Olgica Milenkovic Department of Electrical and Computer Engineering University of Illinois, Urbana-Champaign {ichien3,chaopan2,milenkov}@illinois.edu
Pseudocode Yes Algorithm 1 Training procedure and Algorithm 2 Unlearning procedure in Section A.6.
Open Source Code Yes Our code is available online1. 1https://github.com/thupchnsky/sgc_unlearn
Open Datasets Yes We test our methods on benchmark datasets for graph learning, including Cora, Citseer, Pubmed (Sen et al., 2008; Yang et al., 2016; Fey & Lenssen, 2019) and large-scale dataset ogbnarxiv (Hu et al., 2020) and Amazon co-purchase networks Computers and Photo (Mc Auley et al., 2015; Shchur et al., 2018).
Dataset Splits Yes The data split is public and obtained from PyTorch Geometric Fey & Lenssen (2019). We used the full split option for Cora, Citeseer and Pubmed. Since there is no public split for Computers and Photo, we adopted a similar setting as for the citation networks via random splits (i.e., 500 nodes in the validation set and 1,000 nodes in the test set). The data split for ogbn-arxiv is the public split provided by the Open Graph Benchmark Hu et al. (2020).
Hardware Specification Yes All our experiments were executed on a Linux machine with 48 cores, 376GB of system memory, and two NVIDIA Tesla P100 GPUs with 12GB of GPU memory each.
Software Dependencies No The paper mentions 'PyTorch Geometric' and 'LBFGS as the optimizer' but does not specify their version numbers or other software dependencies with version information.
Experiment Setup Yes Unless specified otherwise, we fix K = 2, δ = 10 4, λ = 10 2, ϵ = 1, α = 0.1 for all experiments, and average the results over 5 independent trails with random initializations.