Adversarial Representation Learning

Follow this topic Ask about this topic

Adversarial representation learning shapes latent features to preserve information needed for a task while hiding or resisting information tied to domains, identities, demographics, views, or attacks. Common approaches use gradient-reversal discriminators, minimax latent perturbations, and disentanglement or orthogonality losses alongside task-prediction, contrastive, or reconstruction objectives. The methods support cross-hospital and cross-subject transfer, speech and vision tasks, privacy and fairness, multimodal clustering, and robust foundation models, evaluated on task performance as well as leakage and out-of-domain robustness. A central challenge is balancing invariance and robustness against losing useful signals, and verifying that gains hold under new shifts and adaptive attacks.

Latest papers

21 papers3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Implicit Feature Reweighting for Label-Free Graph Generalization
Oct 21, 2026Tianjun Yao, Chen Xi, Xinyang Li +1OOD Generalization Graph Representation Learning
1Shenzhen Loop Area Institute · 2Guangzhou University · 3North China Electric Power University +1
Transferable Adversarial Robustness for Speech Foundation Models via Hierarchical Stabilization
Oct 4, 2026Aref Mousavi, Shahab Sherafat, Kiarash Kiani Feriz +4Adversarial Representation Learning Speech Foundation Models
Sharif University of Technology · University of Tehran · New Uzbekistan University +1
Adversarial Consistency-Guided Representation Learning for Multi-view Clustering
Sep 28, 2026Yuchen Lin, Kunpeng Xu, Ying Fang +1Multi-View Consistency Adversarial Representation Learning
School of Computer and Cyber Security, Fujian Normal University, Fuzhou 350000, China · Digital Fujian Internet-of-Things Laboratory of Environmental Monitoring, Fujian Normal University, Fuzhou 350000, China · School of Computer Science, McGill University, Montreal H3A 2A7, Quebec, Canada
Damnatio Memoriae: Adversarially and Selectively Forgetting Identities in the Embedding Space of Face Recognition Models
Sep 22, 2026Ünsal Öztürk, Vedrana Krivokuća Hahn, Sushil Bhattacharjee +1Adversarial Representation Learning Face Recognition
Idiap Research Institute, Martigny, Switzerland · UNIL, Lausanne, Switzerland
NeuroPriv: Adversarial Representation Learning for Privacy in Wearable EEG Systems
Aug 31, 2026Sarmistha Sarna Gomasta, Bhawana Chhaglani, Prashant ShenoyAdversarial Training Electroencephalography
University of Massachusetts Amherst · United States
SISER: Speaker-Invariant Speech Emotion Recognition with Entropy-Based Adversarial Training
Aug 31, 2026Eunseo Choi, Hyunku Kang, Chanwoo KimSpeech Emotion Recognition Invariant Representation Learning
Korea Univiersity, South Korea
The Devil Is in the Leakage: A Disentangled Dual-Purification Framework for High-Fidelity Hairstyle Transfer
Jul 13, 2026Jijie Li, Jiankuo Zhao, Xiangyu Zhu +1Adversarial Representation Learning Image Style Transfer
SAI, UCAS; MAIS, CASIA Beijing, China · CAIR, HKSIS, CAS Hong Kong, China · SCSE, FIE, M.U.S.T Macau, China
Conservative Subject Invariant EMG-based Gesture Recognition
Jul 4, 2026Hamed Rafiei, Ali MousaviEMG-Based Gesture Recognition Adversarial Representation Learning
Department of Electrical Engineering, Center of Excellence on Soft Computing and Intelligent Information Processing, Ferdowsi University of Mashhad, Mashhad, Iran · Department of Computer Engineering, Ne. C., Islamic Azad University, Neyshabur, Iran
Fair Cognitive Impairment Detection Through Unlearning
Jun 17, 2026William Nguyen, Jiali Cheng, Hadi AmiriAdversarial Representation Learning Algorithmic Fairness
University of Massachusetts Lowell, USA
GD-MIL: Grade-Disentangled Multiple Instance Learning for Multimodal Biochemical Recurrence Prediction in Prostate Cancer
Jun 8, 2026Dasari Naga RajuAdversarial Representation Learning Cancer Survival Prediction
TabChange: Precise Attribute Changes in Tabular Data
May 30, 2026Arjun Dahal, Yu Lei, Raghu N. Kacker +1Adversarial Representation Learning Counterfactual Explanations
The University of Texas at Arlington · Arlington, Texas, USA · Information Technology Laboratory +2
Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation
May 25, 2026Ruoxi Cheng, Haoxuan Ma, Zhengfei Hai +6Adversarial Representation Learning Vision-Language Models
Fudan University · Tencent · Nanjing University +3
LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
May 21, 2026Sadia Asif, Mohammad Mohammadi Amiri, Momin Abbas +2Adversarial Representation Learning Privacy-Preserving Language Models
Rensselaer Polytechnic Institute · IBM Research
LASE: Language-Adversarial Speaker Encoding for Indic Cross-Script Identity Preservation
May 1, 2026Venkata Pushpak Teja MentaAdversarial Training Adversarial Representation Learning
Praxel Ventures
Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection
Apr 14, 2026Haifeng Zhang, Qinghui He, Xiuli Bi +3Adversarial Debiasing AI-Generated Image Detection
Chongqing Key Laboratory of Image Cognition, School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China · School of Artificial Intelligence, Chongging Key Laboratory of Image Cognition, Chongging University of Posts and Telecommunications, Chongqing 400065, China · Faculty of Science and Technology of the University of Macau, Macau 999078, China +1
SECURE: Stable Early Collision Understanding via Robust Embeddings in Autonomous Driving
Apr 1, 2026Wenjing Wang, Wenxuan Wang, Songning LaiTraffic Accident Anticipation Adversarial Robustness
Xiamen University Malaysia · Xinjiang University · HKUST(GZ)
Representation-Level Adversarial Regularization for Clinically Aligned Multitask Thyroid Ultrasound Assessment
Mar 22, 2026Dina Salama, Mohamed Mahmoud, Nourhan Bayasi +2Multi-Task Learning Clinical Risk Prediction
University of British Columbia, Vancouver, Canada · University of Calgary, Calgary, Canada
Age Predictors Through the Lens of Generalization, Bias Mitigation, and Interpretability: Reflections on Causal Implications
Mar 17, 2026Debdas Paul, Elisa Ferrari, Irene Gravili +1OOD Generalization Debiased ML
Leibniz Institute on Aging — Fritz Lipmann Institute (FLI), Beutenbergstr. 11, Jena, 100190, Germany.
Learning Clinical Representations Under Systematic Distribution Shift
Mar 7, 2026Yuanyun Zhang, Shi LiOOD Generalization Invariant Representation Learning
Columbia University
Adversarial Batch Representation Augmentation for Batch Correction in High-Content Cellular Screening
Mar 5, 2026Lei Tong, Xujing Yao, Adam Corrigan +6Batch Effect Correction Domain Generalization
Data Sciences and Quantitative Biology, Discovery Sciences, AstraZeneca R&D, Cambridge, UK · School of Computing and Mathematical Sciences, University of Leicester, Leicester, UK · College of Computer and Information Engineering, Nanjing Tech University, Nanjing, China +1
Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study
Feb 17, 2026Sarah Müller, Philipp BerensShortcut Learning Disentangled Representation Learning
Hertie Institute for AI in Brain Health, Faculty of Medicine, University of Tübingen, Germany · Tübingen AI Center, University of Tübingen, Germany

Oct 21, 2026J/K move · Enter open · S save

Implicit Feature Reweighting for Label-Free Graph Generalization

Tianjun Yao, Chen Xi, Xinyang Li, Lixian Zhong

1Shenzhen Loop Area Institute · 2Guangzhou University · 3North China Electric Power University+1

OOD Generalization Graph Representation Learning Adversarial Representation Learning

Open paper AskPDF arXiv

Graph-level out-of-distribution (OOD) generalization is critical for deploying graph neural networks in real-world applications where distribution shifts are inevitable. Existing approaches typically require class labels during representation learning to decide which substructures are predictive, limiting their applicability. We propose SCARCE, a label-free representation-learning framework that yields distribution-shift-robust graph representations from an environment partition of the training graphs alone, whether that partition comes from dataset metadata or, when none is available, from clustering a self-supervised embedding. Our method operates in two stages: (1) a variational graph autoencoder is warm-started for graph reconstruction; and (2) an adversarial confusion mechanism forces the encoder to produce representations from which a discriminator cannot distinguish environments, while preserving graph-reconstruction fidelity. We provide theoretical analysis showing that environment confusion contracts environment-discriminative directions in the representation space, which, under regularized downstream classifiers, is equivalent to imposing a stronger directional penalty on environment-associated features. This feature-reweighting mechanism reduces reliance on spurious correlations without erasing information, offering a label-free, continuous relaxation of last-layer reweighting methods. Experiments on a controlled synthetic datasets and the DrugOOD datasets show that SCARCE achieves state-of-the-art OOD generalization among label-free methods, using no class labels during representation learning.