Information-Theoretic Requirements for Gradient-Based Task Affinity Estimation in Multi-Task Learning
This provides a principled explanation for inconsistent multi-task learning results, addressing a foundational problem for researchers in machine learning and computational biology.
The paper tackled the inconsistent results in multi-task learning by identifying that gradient-based task analysis requires tasks to share training instances to reveal genuine relationships, discovering a sharp phase transition where below 30% overlap correlations are noise and above 40% they reliably recover biological structure, with validation achieving strong correlations and recovering pathway organization.
Multi-task learning shows strikingly inconsistent results -- sometimes joint training helps substantially, sometimes it actively harms performance -- yet the field lacks a principled framework for predicting these outcomes. We identify a fundamental but unstated assumption underlying gradient-based task analysis: tasks must share training instances for gradient conflicts to reveal genuine relationships. When tasks are measured on the same inputs, gradient alignment reflects shared mechanistic structure; when measured on disjoint inputs, any apparent signal conflates task relationships with distributional shift. We discover this sample overlap requirement exhibits a sharp phase transition: below 30% overlap, gradient-task correlations are statistically indistinguishable from noise; above 40%, they reliably recover known biological structure. Comprehensive validation across multiple datasets achieves strong correlations and recovers biological pathway organization. Standard benchmarks systematically violate this requirement -- MoleculeNet operates at <5% overlap, TDC at 8-14% -- far below the threshold where gradient analysis becomes meaningful. This provides the first principled explanation for seven years of inconsistent MTL results.