Auto-weighted Mutli-view Sparse Reconstructive Embedding
This work addresses the challenge of extracting complementary information from multi-view data to improve tasks like dimension reduction, but it appears incremental as it builds on existing multi-view methods.
The authors tackled the problem of multi-view dimension reduction for high-dimensional data by proposing AMSRE, which exploits sparse reconstructive correlations and uses auto-weighting to differentiate view contributions, achieving excellent performance in experiments.
With the development of multimedia era, multi-view data is generated in various fields. Contrast with those single-view data, multi-view data brings more useful information and should be carefully excavated. Therefore, it is essential to fully exploit the complementary information embedded in multiple views to enhance the performances of many tasks. Especially for those high-dimensional data, how to develop a multi-view dimension reduction algorithm to obtain the low-dimensional representations is of vital importance but chanllenging. In this paper, we propose a novel multi-view dimensional reduction algorithm named Auto-weighted Mutli-view Sparse Reconstructive Embedding (AMSRE) to deal with this problem. AMSRE fully exploits the sparse reconstructive correlations between features from multiple views. Furthermore, it is equipped with an auto-weighted technique to treat multiple views discriminatively according to their contributions. Various experiments have verified the excellent performances of the proposed AMSRE.