atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Heterogeneous-Branch Collaborative Learning for Dialogue Generation

AAAI 2023 · Label-efficient and robust learning › Knowledge distillation · approach: Self and data-free distillation · 1 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Add dialogue attribute learning with attribute-specific training subsets (ablation)CDL · DailyDialogDist-1: 0.0177 -> 0.0252Helped
Add orthogonal projection (ablation)CDL · DailyDialogDist-1: 0.0203 -> 0.0252Helped
Add hidden-state negative distillation (ablation)CDL · DailyDialogDist-1: 0.0222 -> 0.0252Helped
Add negative distillation (ablation)CDL · DailyDialogDist-1: 0.0215 -> 0.0252Helped
Use attribute-aware collaborative learning instead of the strongest listed collaborative baselineCDL-IS vs. CL-ILR · DailyDialogDist-2: 0.0686 -> 0.1081Helped
Use attribute-aware collaborative learning instead of the strongest listed collaborative baselineCDL-CI vs. CL-ILR · OpenSubtitlesDist-2: 0.0179 -> 0.0239Helped
Increase branch count from 3 to 4CDL · DailyDialogDist-1: 0.0252 -> 0.0211Mixed

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