Forgetting Fast in Recommender Systems Article Swipe

MAKE IMPACT

Wenyan Liu , Juncheng Wan , Xiaoling Wang , Weinan Zhang , Dell Zhang , Hang Li · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2208.06875

Users of a recommender system may want part of their data being deleted, not only from the data repository but also from the underlying machine learning model, for privacy or utility reasons. Such right-to-be-forgotten requests could be fulfilled by simply retraining the recommendation model from scratch, but that would be too slow and too expensive in practice. In this paper, we investigate fast machine unlearning techniques for recommender systems that can remove the effect of a small amount of training data from the recommendation model without incurring the full cost of retraining. A natural idea to speed this process up is to fine-tune the current recommendation model on the remaining training data instead of starting from a random initialization. This warm-start strategy indeed works for neural recommendation models using standard 1st-order neural network optimizers (like AdamW). However, we have found that even greater acceleration could be achieved by employing 2nd-order (Newton or quasi-Newton) optimization methods instead. To overcome the prohibitively high computational cost of 2nd-order optimizers, we propose a new recommendation unlearning approach AltEraser which divides the optimization problem of unlearning into many small tractable sub-problems. Extensive experiments on three real-world recommendation datasets show promising results of AltEraser in terms of consistency (forgetting thoroughness), accuracy (recommendation effectiveness), and efficiency (unlearning speed). To our knowledge, this work represents the first attempt at fast approximate machine unlearning for state-of-the-art neural recommendation models.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2208.06875

PDF

https://arxiv.org/pdf/2208.06875

OA Status

green

Cited By

3

Related Works

10

OpenAlex ID

https://openalex.org/W4292102111

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4292102111

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2208.06875

Digital Object Identifier

Title

Forgetting Fast in Recommender Systems

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-08-14

Full publication date if available

Authors

Wenyan Liu, Juncheng Wan, Xiaoling Wang, Weinan Zhang, Dell Zhang, Hang Li

List of authors in order

Landing page

https://arxiv.org/abs/2208.06875

Publisher landing page

PDF URL

https://arxiv.org/pdf/2208.06875

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2208.06875

Direct OA link when available

Concepts

Forgetting, Computer science, Recommender system, Retraining, Initialization, Artificial intelligence, Machine learning, Artificial neural network, Consistency (knowledge bases), Speedup, Process (computing), Parallel computing, Operating system, International trade, Linguistics, Business, Philosophy, Programming language

Top concepts (fields/topics) attached by OpenAlex

Cited by

3

Total citation count in OpenAlex

Citations by year (recent)

2025: 1, 2024: 1, 2023: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload