SPARK: Simple and Parameter-Free Knowledge Embedding With Fuzzy Cognitive Maps for Class Incremental Learning
Lists
Only you see this
Abstract
Class incremental learning (CIL) aims to mitigate catastrophic forgetting of previously learned classes when integrating new knowledge. A primary challenge contributing to forgetting is the absence of data from earlier classes. Researchers have designed a variety of methods to solve the problem, among which topology-preserving methods show tremendous potential. However, two problems remain: first, a large hyperparameter search space for constructing and utilizing a complex topology hinders efficient performance optimization, and second, constraining the network to preserve the topology in the objective makes it difficult to optimize. This article proposes SPARK, a simple and parameter-free method by embedding fuzzy cognitive maps, to address the problems. First, we construct a fuzzy cognitive map with nodes representing class prototypes and edges representing interclass similarities. Then, we exploit the fuzzy cognitive map to obtain class-level embedding by aggregating features of other classes for each class. Finally, the class- and sample-level embeddings are fused and fed to the classifier. The proposed method can be easily optimized without introducing additional loss terms and hyperparameters. We theoretically prove that such a simple fuzzy cognitive map embedding can efficiently preserve the structural information of the fuzzy cognitive map. Experimental results indicate that SPARK achieves up to 5.85% higher average accuracy and 8.69% reduction in forgetting compared to baseline methods.
BibTeX
@article{wang2025spark,
author = {Yu Wang and Jiabo Xie and Junyan Zheng and Bingxu Lu and Yanxian Bi and Qinghua Hu},
title = {{SPARK: Simple and Parameter-Free Knowledge Embedding With Fuzzy Cognitive Maps for Class Incremental Learning}},
journal = {IEEE Trans. Fuzzy Systems},
year = {2025},
doi = {10.1109/tfuzz.2025.3568072},
}Loading related content...