Seonglae ChoMTL, Multi Task Model
MoE way
- Individual gating network for each task, rather than a single one for the entire model
- Learn a per-task and per-sample weighting of each of the expert networks (instead of just a per-sample weighting)
Leveraging relationships across tasks
Cross-Task Knowledge Distillation in Multi-Task Recommendation
Multi-task learning (MTL) has been widely used in recommender systems, wherein predicting each type of user feedback on items (e.g, click, purchase) are treated as individual tasks and jointly...
https://arxiv.org/abs/2202.09852
Modeling the Sequential Dependence among Audience Multi-step...
In most real-world large-scale online applications (e.g., e-commerce or finance), customer acquisition is usually a multi-step conversion process of audiences. For example, an...
https://arxiv.org/abs/2105.08489
Behavior
Multi-task Ranking with User Behaviors for Text-video Search | Companion Proceedings of the Web Conference 2022
The signals used for ranking in local search are very different from web search: in addition to (textual) relevance, measures of (geographic) distance between the user and the search result, as well as measures of popularity of the result are important ...
https://dl.acm.org/doi/10.1145/3487553.3524207
Multi-Scale User Behavior Network for Entire Space Multi-Task Learning
Modelling the user's multiple behaviors is an essential part of modern e-commerce, whose widely adopted application is to jointly optimize click-through rate (CTR) and conversion rate (CVR)...
https://arxiv.org/abs/2208.01889
Graph Recommender system
Multi-Task Learning of Graph-based Inductive Representations of Music Content - Spotify Research
Music streaming platforms rely heavily on learning meaningful representations of tracks to surface apt recommendations to users in a number of different use cases. In this work, we consider the task of learning music track representations by leveraging three rich heterogeneous sources of information: (i) organizational information (e.g., playlist co-occurrence), (ii) content information (e.g., audio... View Article
https://research.atspotify.com/publications/multi-task-learning-of-graph-based-inductive-representations-of-music-content/
RL
Multi-Task Fusion via Reinforcement Learning for Long-Term User...
Recommender System (RS) is an important online application that affects billions of users every day. The mainstream RS ranking framework is composed of two parts: a Multi-Task Learning model (MTL)...
https://arxiv.org/abs/2208.04560
