GLUE is a multi-task benchmark for general natural language understanding that includes a diagnostic test suite and finds limited gains from current multi-task learning methods over single-task training.
Sluice networks: Learning what to share between loosely related tasks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Multi-task learning (MTL) allows deep neural networks to learn from related tasks by sharing parameters with other networks. In practice, however, MTL involves searching an enormous space of possible parameter sharing architectures to find (a) the layers or subspaces that benefit from sharing, (b) the appropriate amount of sharing, and (c) the appropriate relative weights of the different task losses. Recent work has addressed each of the above problems in isolation. In this work we present an approach that learns a latent multi-task architecture that jointly addresses (a)--(c). We present experiments on synthetic data and data from OntoNotes 5.0, including four different tasks and seven different domains. Our extension consistently outperforms previous approaches to learning latent architectures for multi-task problems and achieves up to 15% average error reductions over common approaches to MTL.
verdicts
UNVERDICTED 3representative citing papers
Sluice network transfer learning jointly detects infected clients and malicious domains from HTTPS traffic, outperforming separate models and identifying previously unknown threats.
Petro-SAM adapts SAM via a Merge Block for polarized views plus multi-scale fusion and color-entropy priors to jointly achieve grain-edge and lithology segmentation in petrographic images.
citing papers explorer
-
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
GLUE is a multi-task benchmark for general natural language understanding that includes a diagnostic test suite and finds limited gains from current multi-task learning methods over single-task training.
-
Joint Detection of Malicious Domains and Infected Clients
Sluice network transfer learning jointly detects infected clients and malicious domains from HTTPS traffic, outperforming separate models and identifying previously unknown threats.
-
From Boundaries to Semantics: Prompt-Guided Multi-Task Learning for Petrographic Thin-section Segmentation
Petro-SAM adapts SAM via a Merge Block for polarized views plus multi-scale fusion and color-entropy priors to jointly achieve grain-edge and lithology segmentation in petrographic images.