A Survey on Rank Aggregation

A Survey on Rank Aggregation

Siyi Wang, Qi Deng, Shiwei Feng, Hong Zhang, Chao Liang

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Survey Track. Pages 8281-8289. https://doi.org/10.24963/ijcai.2024/915

Rank aggregation (RA), the technique of combining multiple basic rankings into a consensus one, plays an important role in social choices, bioinformatics, information retrieval, metasearch, and recommendation systems. Although recent years have witnessed remarkable progress in RA, the absence of a systematic overview motivates us to conduct a comprehensive survey including both classic algorithms and the latest advances in RA study. Specifically, we first discuss the challenges of RA research, then present a systematic review with a fine-grained taxonomy to introduce representative algorithms in unsupervised RA, supervised RA, as well as the previously overlooked semi-supervised RA. Within each category, we not only summarize the common ideas of similar methods, but also discuss their strengths and weaknesses. Particularly, to investigate the performance difference of different types of RA methods, we conduct the largest scale of comparative evaluation to date of 27 RA methods on 7 public datasets from person re-identification, recommendation systems, bioinformatics and social choices. Finally, we raise two open questions in the current RA research and make our comments about future trends in the context of the latest research progress.
Keywords:
Data Mining: DM: Information retrieval
Search: S: Search and machine learning