no code implementations • 9 Aug 2022 • Qihua Zhang, Junning Liu, Yuzhuo Dai, Yiyan Qi, Yifan Yuan, Kunlun Zheng, Fan Huang, Xianfeng Tan
The mainstream RS ranking framework is composed of two parts: a Multi-Task Learning model (MTL) that predicts various user feedback, i. e., clicks, likes, sharings, and a Multi-Task Fusion model (MTF) that combines the multi-task outputs into one final ranking score with respect to user satisfaction.
no code implementations • 26 Oct 2021 • Junning Liu, Zijie Xia, Yu Lei, Xinjian Li, Xu Wang
For example, when using MTL to model various user behaviors in RS, if we differentiate new users and new items from old ones, there will be a cartesian product style increase of tasks with multi-dimensional relations.
6 code implementations • RecSys 2020 • Hongyan Tang, Junning Liu, Ming Zhao, Xudong Gong
Moreover, through extensive experiments across SOTA MTL models, we have observed an interesting seesaw phenomenon that performance of one task is often improved by hurting the performance of some other tasks.