Copertina

Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignment

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xian, Guanmeng, Yang, Ning, Yu, Philip S.
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Band Together: Untargeted Adversarial Training with Multimodal Coordination against Evasion-based Promotion Attacks
di: Xian, Guanmeng, et al.
Pubblicazione: (2026)

TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributions
di: YuHang, Wang, et al.
Pubblicazione: (2025)

Provable Unrestricted Adversarial Training without Compromise with Generalizability
di: Zhang, Lilin, et al.
Pubblicazione: (2023)

Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation
di: Zhang, Lilin, et al.
Pubblicazione: (2026)

ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Driving
di: Nie, Tong, et al.
Pubblicazione: (2026)

Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization
di: Saberi, Amir Hossein, et al.
Pubblicazione: (2024)

Beyond Rigid Alignment: Graph Federated Learning via Dual Manifold Calibration
di: Yu, Wentao, et al.
Pubblicazione: (2026)

TCRL: Temporal-Coupled Adversarial Training for Robust Constrained Reinforcement Learning in Worst-Case Scenarios
di: Xu, Wentao, et al.
Pubblicazione: (2026)

Manifold Approximation leads to Robust Kernel Alignment
di: Islam, Mohammad Tariqul, et al.
Pubblicazione: (2025)

Ensemble of Pre-Trained Models for Long-Tailed Trajectory Prediction
di: Thuremella, Divya, et al.
Pubblicazione: (2025)

Adversarial Preference Learning for Robust LLM Alignment
di: Wang, Yuanfu, et al.
Pubblicazione: (2025)

Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Prompting
di: Tsai, Yun-Da, et al.
Pubblicazione: (2024)

IIKL: Isometric Immersion Kernel Learning with Riemannian Manifold for Geometric Preservation
di: Chen, Zihao, et al.
Pubblicazione: (2025)

Robust off-policy Reinforcement Learning via Soft Constrained Adversary
di: Nakanishi, Kosuke, et al.
Pubblicazione: (2024)

ARTA: Adversarial-Robust Multivariate Time--Series Anomaly Detection via Sparsity-Constrained Perturbations
di: Hojjati, Hadi, et al.
Pubblicazione: (2026)

Improving Adversarial Transferability via Model Alignment
di: Ma, Avery, et al.
Pubblicazione: (2023)

Long-Tailed Data Classification by Increasing and Decreasing Neurons During Training
di: Sakai, Taigo, et al.
Pubblicazione: (2025)

Robust and Computationally Efficient Linear Contextual Bandits under Adversarial Corruption and Heavy-Tailed Noise
di: Tani, Naoto, et al.
Pubblicazione: (2026)

Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Training
di: Dong, Junhao, et al.
Pubblicazione: (2024)

Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment
di: Cho, Youngjae, et al.
Pubblicazione: (2026)

Personalized Federated Learning on Heterogeneous and Long-Tailed Data via Expert Collaborative Learning
di: Lv, Fengling, et al.
Pubblicazione: (2024)

On the Robustness of Adversarial Training Against Uncertainty Attacks
di: Ledda, Emanuele, et al.
Pubblicazione: (2024)

Conformal Tail Risk Control for Large Language Model Alignment
di: Chen, Catherine Yu-Chi, et al.
Pubblicazione: (2025)

Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Training
di: Park, Leo Hyun, et al.
Pubblicazione: (2024)

Efficient Manifold-Constrained Neural ODE for High-Dimensional Datasets
di: Guo, Muhao, et al.
Pubblicazione: (2025)

Beyond Alignment: Expanding Reasoning Capacity via Manifold-Reshaping Policy Optimization
di: Wang, Dayu, et al.
Pubblicazione: (2026)

The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning
di: Zhuang, Ren, et al.
Pubblicazione: (2026)

Understanding the Impact of Differentially Private Training on Memorization of Long-Tailed Data
di: Zhang, Jiaming, et al.
Pubblicazione: (2026)

Space Alignment Matters: The Missing Piece for Inducing Neural Collapse in Long-Tailed Learning
di: Wang, Jinping, et al.
Pubblicazione: (2025)

Adapting to Evolving Adversaries with Regularized Continual Robust Training
di: Dai, Sihui, et al.
Pubblicazione: (2025)

Ignition Phase : Standard Training for Fast Adversarial Robustness
di: Yu-Hang, Wang, et al.
Pubblicazione: (2025)

Constrained Adversarial Perturbation
di: Nishad, Virendra, et al.
Pubblicazione: (2025)

Alignment-Based Adversarial Training (ABAT) for Improving the Robustness and Accuracy of EEG-Based BCIs
di: Chen, Xiaoqing, et al.
Pubblicazione: (2024)

Random Forest-Supervised Manifold Alignment
di: Rhodes, Jake S., et al.
Pubblicazione: (2024)

Robust Multi-Manifold Clustering via Simplex Paths
di: Chen, Haoyu, et al.
Pubblicazione: (2025)

Long-Tailed Recognition via Information-Preservable Two-Stage Learning
di: Lin, Fudong, et al.
Pubblicazione: (2025)

Learning Flow Distributions via Projection-Constrained Diffusion on Manifolds
di: Trupin, Noah, et al.
Pubblicazione: (2026)

Manifold-Aware Perturbations for Constrained Generative Modeling
di: Keegan, Katherine, et al.
Pubblicazione: (2026)

MCNC: Manifold-Constrained Reparameterization for Neural Compression
di: Thrash, Chayne, et al.
Pubblicazione: (2024)

Listwise Preference Alignment Optimization for Tail Item Recommendation
di: Li, Zihao, et al.
Pubblicazione: (2025)