Space Alignment Matters: The Missing Piece for Inducing Neural Collapse in Long-Tailed Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Jinping, Gao, Zhiqiang, Xie, Zhiwu
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View
by: Wang, Jinping, et al.
Published: (2026)

Escaping Optimization Stagnation: Taking Steps Beyond Task Arithmetic via Difference Vectors
by: Wang, Jinping, et al.
Published: (2025)

Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware Minimization
by: Wang, Jinping, et al.
Published: (2026)

Heterogeneous Learning Rate Scheduling for Neural Architecture Search on Long-Tailed Datasets
by: Tang, Chenxia
Published: (2024)

PAWN: Piece Value Analysis with Neural Networks
by: Tang, Ethan, et al.
Published: (2026)

Towards Piece-by-Piece Explanations for Chess Positions with SHAP
by: Spinnato, Francesco
Published: (2025)

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

Pavement Missing Condition Data Imputation through Collective Learning-Based Graph Neural Networks
by: Yu, Ke, et al.
Published: (2026)

Representational Alignment with Chemical Induced Fit for Molecular Relational Learning
by: Zhang, Peiliang, et al.
Published: (2025)

The Prevalence of Neural Collapse in Neural Multivariate Regression
by: Andriopoulos, George, et al.
Published: (2024)

Momentum Boosted Episodic Memory for Improving Learning in Long-Tailed RL Environments
by: Fernandes, Dolton, et al.
Published: (2025)

Decoupled Federated Learning on Long-Tailed and Non-IID data with Feature Statistics
by: Chen, Zhuoxin, et al.
Published: (2024)

Best-of-Tails: Bridging Optimism and Pessimism in Inference-Time Alignment
by: Hsu, Hsiang, et al.
Published: (2026)

A Scalable Curiosity-Driven Game-Theoretic Framework for Long-Tail Multi-Label Learning in Data Mining
by: Yang, Jing, et al.
Published: (2026)

Layer Collapse Can be Induced by Unstructured Pruning
by: Liao, Zhu, et al.
Published: (2024)

Vision-Based Generic Potential Function for Policy Alignment in Multi-Agent Reinforcement Learning
by: Ma, Hao, et al.
Published: (2025)

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

Graph Similarity Computation via Interpretable Neural Node Alignment
by: Wang, Jingjing, et al.
Published: (2024)

The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
by: Springer, Max, et al.
Published: (2026)

A Tale of Tails: Model Collapse as a Change of Scaling Laws
by: Dohmatob, Elvis, et al.
Published: (2024)

rETF-semiSL: Semi-Supervised Learning for Neural Collapse in Temporal Data
by: Xie, Yuhan, et al.
Published: (2025)

Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples
by: Gao, Chengqian, et al.
Published: (2025)

Not All Timesteps Matter Equally: Selective Alignment Knowledge Distillation for Spiking Neural Networks
by: Sun, Kai, et al.
Published: (2026)

On the Collapse Errors Induced by the Deterministic Sampler for Diffusion Models
by: Zhang, Yi, et al.
Published: (2025)

Why Do Neural Networks Forget: A Study of Collapse in Continual Learning
by: Zhu, Yunqin, et al.
Published: (2026)

Directional Neural Collapse Explains Few-Shot Transfer in Self-Supervised Learning
by: Luthra, Achleshwar, et al.
Published: (2026)

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning
by: Xu, Yuhang, et al.
Published: (2026)

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

Preventing Model Collapse via Contraction-Conditioned Neural Filters
by: Han, Zongjian, et al.
Published: (2025)

Enhancing Pre-Trained Model-Based Class-Incremental Learning through Neural Collapse
by: He, Kun, et al.
Published: (2025)

REMIND: Rethinking Medical High-Modality Learning under Missingness--A Long-Tailed Distribution Perspective
by: Wu, Chenwei, et al.
Published: (2026)

Adaptive Kernel Design for Bayesian Optimization Is a Piece of CAKE with LLMs
by: Suwandi, Richard Cornelius, et al.
Published: (2025)

OSDTW: Optimal Shared Depth and Task Weighting for Long-Tailed Recognition
by: Chu, Chang, et al.
Published: (2026)

Mitigating Long-Tailed Anomaly Score Distributions with Importance-Weighted Loss
by: Lee, Jungi, et al.
Published: (2026)

Can We Understand Plasticity Through Neural Collapse?
by: Bonifazi, Guglielmo, et al.
Published: (2024)

Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networks
by: Gong, Yanxiang, et al.
Published: (2022)

Risk-Informed Diffusion Transformer for Long-Tail Trajectory Prediction in the Crash Scenario
by: Chen, Junlan, et al.
Published: (2025)

HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment
by: Liu, Zhanyu, et al.
Published: (2026)

DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment
by: Zhao, Gongpei, et al.
Published: (2024)

Collapsed Inference for Bayesian Deep Learning
by: Zeng, Zhe, et al.
Published: (2023)