AI RESEARCH
CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations
arXiv CS.LG
•
ArXi:2606.02221v1 Announce Type: cross Multi-task learning (MTL) aims to construct a joint model for multiple tasks by sharing a common representation across domains. To achieve this goal, existing optimization-centric methods either balance task gradients or modify the shared architecture. However, as these approaches remain agnostic to the content of the shared representation, they fail to disentangle task-relevant structure from spurious context, leading to negative transfer and poor generalization.