Gradient magnitude balancing for multitask learning

Methods that equalize gradient magnitudes across tasks to improve multitask optimization, outperforming GradNorm on vision and domain adaptation benchmarks.

2 members. Each node is clickable.

Loading graph…

Drawn from 1 source

The papers/notes whose extracted claims & findings make up this cluster.

Dual-Balancing for Multi-Task Learning2 members

Bridges (2)

Other communities that share members with this one — cross-cutting threads or papers that sit at the seam between two themes.

Dual-balancing multi-task learning2 shared
Dual balancing multi-task learning1 shared

Claims (1)

The proposed gradient-magnitude balancing method consistently outperforms GradNorm, as it guarantees equal gradient magnitudes and considers update magnitude.Advantage over GradNorm.

Findings (1)

The gradient-magnitude balancing method outperforms GradNorm on NYUv2, Cityscapes, Office-31, Office-Home.Comparison of gradient-magnitude balancing with GradNorm.