Uncertainty Weighting (UW)

Loss balancing using homoscedastic uncertainty.

Neighborhood — ranked by edge-count

artifact

Lin 2023 Dual-Balancing for Multi-Task Learning
mentions
The paper proposing the Dual-Balancing Multi-Task Learning method.

cosine ≥ 0.65 · no typed edge

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

Equal Weighting (EW)method0.763
Baseline that minimizes sum of task losses with equal weights.
Internal uncertaintyconcept0.746
The model's internal representation of uncertainty hypothesized to trigger self-reflection
variant of uncertain significance (VUS)concept0.729
Genetic variants whose clinical impact is unknown; a key motivation for the work, ~2M of which are explained.
Table 1: Sources of Uncertainty Scored by Expected Free Energy and the Behaviors Entailedconcept0.723
Summary table mapping uncertainty types to free energy formulations and corresponding behaviors
Object pronoun upweightingconcept0.720
The other pathway in the 'her' subnetwork, where the verb 'lost' upweights object pronouns (including 'her').
Equal Weightingframework0.719
Baseline MTL approach minimizing sum of task losses with equal weights; suffers from task balancing
Weight spaceconcept0.712
The space of the model's parameter matrices, where VPD operations take place.
Random Loss Weighting (RLW)method0.711
Samples task weights from a standard normal distribution.