concept
active
concept:task-balancingTask balancing
The problem of ensuring all tasks in MTL perform well, avoiding dominance by some tasks.
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Core challenge where disparity in loss and gradient scales among tasks leads to performance compromises
- Motivation for the proposed method.
- The paper identifies task difficulty as a key moderator: easy MMLU questions show performative CoT, hard GPQA-Diamond questions show genuine reasoning
- Novel task asking which of two sentences received a stronger injection, using matched-pairs design to control for positional bias
- Novel MTL method combining loss-scale and gradient-magnitude balancing
- One of four ToM tasks analyzed; requires inferring speaker intent from indirect hints; scored 0/1.
- Addressing disparity in loss magnitudes across tasks at the loss level
- Coefficient weighting each task loss in the MTL objective.