AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Heterogeneous Domain Adaptation With Adversarial Neural Representation Learning: Experiments on E-Commerce and Cybersecurity

Mohammadreza Reza Ebrahimi, Yidong Chai, Hao Helen Zhang, Hsinchun Chen

TPAMI 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 19 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
add shared dictionary learning (ablation)HANDA · Office31-Caltech256 SURF to DeCAF (average)accuracy: 23.6 -> 97.2Improved
add adversarial kernel matching (ablation)HANDA · Office31-Caltech256 SURF to DeCAF (average)accuracy: 93.1 -> 97.2Improved
use adversarial kernel matching loss instead of entropy-based alignment (ablation)HANDA · Office31-Caltech256 SURF to DeCAF (average)accuracy: 96.3 -> 97.2Improved
add shared dictionary learning (ablation)HANDA · Reuters multilingual EN→SP (10 labeled/class)accuracy: 23.4 -> 74.5Improved
add adversarial kernel matching (ablation)HANDA · Reuters multilingual EN→SP (10 labeled/class)accuracy: 68.0 -> 74.5Improved
add adversarial kernel matching (ablation)HANDA · Reuters multilingual EN→SP (20 labeled/class)accuracy: 75.7 -> 79.8Improved
use adversarial kernel matching loss instead of entropy-based alignment (ablation)HANDA · Reuters multilingual EN→SP (10 labeled/class)accuracy: 73.7 -> 74.5Improved
train shared dictionary and adversarial matching jointly rather than sequentially (ablation)HANDA · Reuters multilingual EN→SP (10 labeled/class)accuracy: 71.1 -> 74.5Improved
use 2 hidden layers instead of 1 (ablation)HANDA feature extractor · Reuters multilingual EN→SP (10 labeled/class)accuracy: 73.0 -> 74.5Improved
use 2 hidden layers instead of 5 (ablation)HANDA feature extractor · Reuters multilingual EN→SP (10 labeled/class)accuracy: 72.3 -> 74.5Improved
use 3 hidden layers instead of 2 (ablation)HANDA feature extractor · Reuters multilingual EN→SP (10 and 20 labels)accuracy: 74.5 -> 74.4; 79.8 -> 80.0No clear effect
adapt English dark web markets to Russian with HANDA vs no-DA neural networkHANDA · Dark web cyber threat detection (Russian)AUC: 0.96 -> 0.98Improved

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