AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Learning to Multitask

Yu Zhang, Ying Wei, Qiang Yang

NeurIPS 2018 · Graph learning › Graph algorithms and clustering · approach: Neural combinatorial optimization on graphs · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
learn the task covariance from data rather than imposing an explicit task-covariance assumptionL2MT · MIT-Indoor-Scene, Caltech256, 20newsgroup, and RCV1relative test errorImproved
fine-tune the VGG-19 FC layers using the multitask objective (ablation)L2MT · Caltech256 and MIT-Indoor-Sceneaverage test error: reduced by about 5%Improved
replace the proposed estimation and link functions with the alternative formulations (ablation)L2MT · Benchmark datasetstest error: about 2% relative increase on the test errorHurt
increase LGNN depth from 1 layer to 2 or 3 layers (ablation)L2MT · 20newsgrouprelative test errorImproved
increase LGNN depth beyond 3 layers (ablation)L2MT · 20newsgrouprelative test errorHurt
increase the LGNN latent dimension to a larger value (ablation)L2MT · 20newsgrouprelative test errorHurt
increase the number of historical multitask problems used for training (ablation)L2MT · 20newsgrouptest errorImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy