GradNorm Loss Weighting for Multi-Task Learning: Weights and Losses over Training (2D)
Bars of loss weights and weighted gradient norms, dots tracing the four task losses and a plot of the weights over training. The same shared model as the 3D scene with numerical checks.
A shared trunk feeds three task-specific heads, and this simulator lets you switch between the three standard ways a real multi-task network decides how hard each task is allowed to pull on those shared weights: naive equal weighting, Kendall's learned-uncertainty weighting, and Chen et al.'s GradNorm, which actively balances each task's gradient magnitude against its relative training pace. Colored particle streams flow from each task head back into the trunk with a size and speed set by that task's live gradient norm, while side panels track every task's evolving loss weight and gradient norm step by step — so you can watch, in real time, a hard task get starved under equal weighting and then rescued the moment GradNorm or uncertainty weighting takes over.
Bars of loss weights and weighted gradient norms, dots tracing the four task losses and a plot of the weights over training. The same shared model as the 3D scene with numerical checks.
2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install