Task balancing is still an open problem in multi-task learning.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• task balancing problemquestion0.830
  Core challenge where disparity in loss and gradient scales among tasks leads to performance compromises
• Dual-Balancing Multi-Task Learningframework0.822
  Novel MTL method combining loss-scale and gradient-magnitude balancing
• Task balancingconcept0.816
  The problem of ensuring all tasks in MTL perform well, avoiding dominance by some tasks.
• Multi-Task Learningconcept0.805
  Learning paradigm that jointly learns multiple related tasks using a single model
• Task balancing requires simultaneous consideration of both loss scales and gradient magnitudesclaim0.801
  Core interpretive position of DB-MTL: complementarity of loss and gradient perspectives
• There are fewer representations competent for N tasks than M<N tasks, so training more general models should yield fewer possible solutionshypothesis0.769
  Selective pressure toward convergence via task generality
• For a given task, the number of all sequences which work is tiny by comparison with the huge number of all possible sequences; less than a trillionth of all 6 × 10^23 possible sequences actually work well enough.claim0.764
  A combinatorial argument that good sequences are astronomically rare, emphasizing the difficulty of discovery.
• Parallel sub-tasks within skills and across skill families should produce parallel outputs for legibility.claim0.763