NetEase Smart Enterprise Tech+
Feb 28, 2024 · Artificial Intelligence
Mastering Multi-Task Learning: Network Designs & Loss Balancing
This article reviews the challenges of multi‑task learning, compares various network architectures such as hard‑parameter sharing, MMoE, CGC, and PLE, and examines loss‑balancing techniques like GradNorm, Dynamic Weight Average and task‑prioritization, offering insights on how to mitigate the “seesaw” effect and improve overall performance.
AI researchMulti-Task Learningdynamic weighting
0 likes · 15 min read
