Measuring Fine-Grained Relatedness in Multitask Learning via Data Attribution
This work addresses a critical open problem in MTL for researchers and practitioners by providing an efficient solution to enhance model performance, though it is incremental as it adapts existing influence functions to MTL.
The paper tackles the challenge of measuring task relatedness and mitigating negative transfer in Multitask Learning (MTL) by extending data attribution to MTL, resulting in a fine-grained, instance-level measure that enables data selection strategies to improve model performance consistently.
Measuring task relatedness and mitigating negative transfer remain a critical open challenge in Multitask Learning (MTL). This work extends data attribution -- which quantifies the influence of individual training data points on model predictions -- to MTL setting for measuring task relatedness. We propose the MultiTask Influence Function (MTIF), a method that adapts influence functions to MTL models with hard or soft parameter sharing. Compared to conventional task relatedness measurements, MTIF provides a fine-grained, instance-level relatedness measure beyond the entire-task level. This fine-grained relatedness measure enables a data selection strategy to effectively mitigate negative transfer in MTL. Through extensive experiments, we demonstrate that the proposed MTIF efficiently and accurately approximates the performance of models trained on data subsets. Moreover, the data selection strategy enabled by MTIF consistently improves model performance in MTL. Our work establishes a novel connection between data attribution and MTL, offering an efficient and fine-grained solution for measuring task relatedness and enhancing MTL models.