Task groupings are inferred from one-step gradient distances between tasks at initialization and clustered with graph attention networks, matching TAG/HOA performance at lower cost.
Multitask learning: A knowledge-based source of inductive bias,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Efficient Task Grouping Through Samplewise Optimisation Landscape Analysis
Task groupings are inferred from one-step gradient distances between tasks at initialization and clustered with graph attention networks, matching TAG/HOA performance at lower cost.