Multi-task models typically output only marginal probabilities per task, discarding joint information. This paper presents a framework that approximates the joint distribution of task labels through targeted pairwise relationships, avoiding the complexity of full joint modeling. By adding auxiliary heads that capture covariance between tasks, the approach improves . The method was deployed on YouTube's Notifications, Homepage, and Watch Next surfaces, yielding gains in accuracy and user satisfaction. A workflow template is provided to help others adopt the technique.
Modeling pairwise task relationships improves multi-task recommendation systems
A proposed framework approximates the joint distribution of task labels using pairwise interactions, boosting accuracy and user satisfaction on YouTube surfaces
Big Tech
Victor Zhang · Yiping Yuan · Florian Raudies · Bosun Adeoti · Brian Y. C. Leung · Sanjay Surendranath Girija · +1 more
Research Digest··2 min read
In one line
Learning pairwise cross-task relationships improves multi-task recommendation accuracy and user satisfaction.
Before you read this
Two ideas this paper builds onRead it as
Zhang et al. propose a framework for multi-task models that learns explicit cross-task relationships by approximating the joint distribution of task labels via pairwise interactions.
The authors augment existing multi-task models with auxiliary heads that capture pairwise relationships between tasks, specifically covariance between task labels.
How it works
before and afterThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.