Flexible Multi-task Networks by Learning Parameter Allocation

ICLR 2020 Krzysztof MaziarzEfi KokiopoulouAndrea GesmundoLuciano SbaizGabor BartokJesse Berent

This paper proposes a novel learning method for multi-task applications. Multi-task neural networks can learn to transfer knowledge across different tasks by using parameter sharing... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Multi-Task Learning OMNIGLOT Gumbel-Matrix Routing Average Accuracy 93.52 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet