A multi-task learning method combining a shared encoder, per-task encoders, and coefficient-similarity penalties, with generalization bounds and empirical gains on simulated and PDX cancer data.
For instance, Tang and Song (2016) proposed a regularized fusion method to identify and merge inter-task homogeneous parameter clusters in regression analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-task Learning for Heterogeneous Data via Integrating Shared and Task-Specific Encodings
A multi-task learning method combining a shared encoder, per-task encoders, and coefficient-similarity penalties, with generalization bounds and empirical gains on simulated and PDX cancer data.