Distillation based Multi-task Learning: A Candidate Generation Model for Improving Reading Duration
This work addresses user experience issues in recommender systems by improving candidate generation, though it is incremental as it builds on existing multi-task learning and distillation methods.
The paper tackles the problem of candidate generation in feeds recommendation by modeling both click and reading duration to avoid recommending low-quality items, and shows that their distillation-based multi-task learning approach significantly outperforms competitors in duration modeling.
In feeds recommendation, the first step is candidate generation. Most of the candidate generation models are based on CTR estimation, which do not consider user's satisfaction with the clicked item. Items with low quality but attractive title (i.e., click baits) may be recommended to the user, which worsens the user experience. One solution to this problem is to model the click and the reading duration simultaneously under the multi-task learning (MTL) framework. There are two challenges in the modeling. The first one is how to deal with the zero duration of the negative samples, which does not necessarily indicate dislikes. The second one is how to perform multi-task learning in the candidate generation model with double tower structure that can only model one single task. In this paper, we propose an distillation based multi-task learning (DMTL) approach to tackle these two challenges. We model duration by considering its dependency of click in the MTL, and then transfer the knowledge learned from the MTL teacher model to the student candidate generation model by distillation. Experiments conducted on dataset gathered from traffic logs of Tencent Kandian's recommender system show that the proposed approach outperforms the competitors significantly in modeling duration, which demonstrates the effectiveness of the proposed candidate generation model.