AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Multiplicative Multitask Feature Learning

Xin Wang, Jinbo Bi, Shipeng Yu, Jiangwen Sun, Minghu Song

JMLR 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 1 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
use MMTFL(2,1) (l2 on c, l1 on beta) instead of MMTFL(2,2)multiplicative MTFL · Synthetic D1 (33% training data)R2: 0.79 -> 0.86Improved
use MMTFL(2,1) instead of MMTFL(1,1)multiplicative MTFL · Synthetic D1 (25% training data)R2: 0.54 -> 0.73Improved
use MMTFL(1,2) instead of MMTFL(2,2)multiplicative MTFL · Synthetic D2 (33% training data)R2: 0.69 -> 0.83Improved
use MMTFL(1,2) instead of MMTFL(2,1)multiplicative MTFL · Synthetic D1 (25% training data)R2: 0.73 -> 0.42Hurt
use multiplicative MMTFL(2,1) instead of additive dirty model DMTLmultitask feature learning · Synthetic D1 (33% training data)R2: 0.73 -> 0.86Improved
use multiplicative MMTFL(1,2) instead of additive robust MTFLmultitask feature learning · Synthetic D2 (50% training data)R2: 0.83 -> 0.97Improved
use multitask learning DMTL instead of single task learningsingle task learning · SARCOS (25% training data)R2: 0.78 -> 0.90Improved
use MMTFL(1,2) instead of MMTFL(2,2)multiplicative MTFL · SARCOS (33% training data)R2: 0.90 -> 0.89Hurt
use MMTFL(1,2) instead of rMTFLmultitask feature learning · USPS (33% training data)F1 score: 0.90 -> 0.91Improved
use MMTFL(2,1) instead of DMTLmultitask feature learning · SARCOS (50% training data)R2: 0.87 -> 0.91Improved
increase training data fraction from 25% to 50% for MMTFL(1,2)MMTFL(1,2) · Synthetic D2R2: 0.49 -> 0.97Improved

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