# Knowledge Swapping via Learning and Unlearning

Source: [Knowledge Swapping via Learning and Unlearning](<https://www.sota2.com/research/paper/68fa77081e209131cea70a07>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:08:06.137Z

Authors: Mingyu Xing, Lechao Cheng, Shengeng Tang, Yaxiong Wang, Zhun Zhong, Meng Wang

Published: 2025-02-12T02:37:16.000Z

## Abstract

We introduce \\textbf{Knowledge Swapping}, a novel task designed to selectively regulate knowledge of a pretrained model by enabling the forgetting of user\\-specified information, retaining essential knowledge, and acquiring new knowledge simultaneously. By delving into the analysis of knock-on feature hierarchy, we find that incremental learning typically progresses from low\\-level representations to higher\\-level semantics, whereas forgetting tends to occur in the opposite direction\\-starting from high-level semantics and moving down to low-level features. Building upon this, we propose to benchmark the knowledge swapping task with the strategy of \\textit{Learning Before Forgetting}. Comprehensive experiments on various tasks like image classification, object detection, and semantic segmentation validate the effectiveness of the proposed strategy. The source code is available at \\href{https://github.com/xingmingyu123456/KnowledgeSwapping}{https://github.com/xingmingyu123456/KnowledgeSwapping}.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2502.08075>)

[PDF](<https://arxiv.org/pdf/2502.08075.pdf>)