arXiv:2509.16959v1 Announce Type: cross Abstract: When different objectives conflict with each other in multi-task learning, gradients begin to interfere and slow convergence, thereby reducing the final model's performance. To address this, we introduce a scheduler that computes gradient interference, constructs an interference graph, and then applies greedy graph-coloring to partition tasks into groups that align well with each other. At each training step, only one group (color class) of tasks are activated. The grouping partition is constantly recomputed as task relationships evolve throughout training. By ensuring that each mini-batch contains only tasks that pull the model in the same direction, our method improves the effectiveness of any underlying multi-task learning optimizer without additional tuning. Since tasks within these groups will update in compatible directions, model performance will be improved rather than impeded. Empirical results on six different datasets show that this interference-aware graph-coloring approach consistently outperforms baselines and state-of-the-art multi-task optimizers.