AI Paper Atlas

Research map / Optimization / Optimizers

Multi-Objective Deep Learning with Adaptive Reference Vectors

Weiyu Chen, James Kwok

NeurIPS 2022 · Optimization › Optimizers · approach: Multi-objective gradient methods · 4 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
adaptive reference vectors (GMOOAR-U) instead of fixed (COSMOS)COSMOS · Multi-MNISTHV: 2.95 -> 3.02Improved
adaptive reference vectors (GMOOAR-U) instead of fixed (COSMOS)COSMOS · Multi-Fashion+MNISTHV: 2.82 -> 2.91Improved
adaptive reference vectors (GMOOAR-U) instead of fixed (COSMOS)COSMOS · AdultHV: 3.336 -> 3.344Improved
adaptive reference vectors (GMOOAR-U) instead of fixed (COSMOS)COSMOS · CelebA-Hard (2 tasks)HV: 2.217 -> 2.217No clear effect
adaptive reference vectors (GMOOAR-U) instead of fixed (COSMOS)COSMOS · CelebA-Easy (2 tasks)HV: 3.700 -> 3.710Improved
adaptive reference vectors (GMOOAR-U) instead of fixed (COSMOS)COSMOS · CelebA 5 tasksHV: 11.56 -> 15.19Improved
adaptive reference vectors (GMOOAR-U) instead of fixed (COSMOS)COSMOS · CelebA 15 tasksHV: 1805 -> 4057Improved
use HV-based quality function (GMOOAR-HV) instead of uniformity (GMOOAR-U)GMOOAR-U · CelebA-Hard (2 tasks)HV: 2.217 -> 2.222Improved
use HV-based quality function (GMOOAR-HV) instead of uniformity (GMOOAR-U)GMOOAR-U · Multi-FashionHV: 2.33 -> 2.33No clear effect
use HV-based quality function (GMOOAR-HV) instead of uniformity (GMOOAR-U)GMOOAR-U · Multi-task learning runtimeruntime: 288 -> 348Hurt
adaptive RVs overhead relative to COSMOSCOSMOS · Multi-task learningnumber of parameters: 43,058 -> 43,685No clear effect
too small RV learning rate alpha (ablation)GMOOAR-U · CompassHVHurt

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