Gene Incremental Learning for Single-Cell Transcriptomics

TL;DR

This paper introduces a novel framework for incremental learning of genes in single-cell transcriptomics, addressing the forgetting problem and establishing a comprehensive benchmark for this emerging research area.

Contribution

It pioneers gene incremental learning in biological data, adapting class incremental methods to mitigate gene forgetting, and provides a complete evaluation benchmark.

Findings

Gene forgetting occurs in incremental learning scenarios.

Adapting class incremental methods reduces gene forgetting.

The proposed framework is effective and well-evaluated.

Abstract

Classes, as fundamental elements of Computer Vision, have been extensively studied within incremental learning frameworks. In contrast, tokens, which play essential roles in many research fields, exhibit similar characteristics of growth, yet investigations into their incremental learning remain significantly scarce. This research gap primarily stems from the holistic nature of tokens in language, which imposes significant challenges on the design of incremental learning frameworks for them. To overcome this obstacle, in this work, we turn to a type of token, gene, for a large-scale biological dataset--single-cell transcriptomics--to formulate a pipeline for gene incremental learning and establish corresponding evaluations. We found that the forgetting problem also exists in gene incremental learning, thus we adapted existing class incremental learning methods to mitigate the forgetting of genes. Through extensive experiments, we demonstrated the soundness of our framework design and evaluations, as well as the effectiveness of our method adaptations. Finally, we provide a complete benchmark for gene incremental learning in single-cell transcriptomics.