Finding score-based representative samples for cancer risk prediction

Jun Liao, Hao Luo, Xuewen Yan, Ting Ye, Shanshan Huang, Li Liu

Abstract: Highlights•A general score-based framework is presented to explicitly perform representative sampling tasks.•The framework ensembles score functions to assess representative levels for each sample.•Advanced explainable models are leveraged to find representative samples.•Performances can be improved by weight optimization using FISTA Algorithm on cancer risk prediction.•Our approach outperforms the state-of-the-arts on four cancer risk datasets with different challenges.