Cover Image

Feature Dynamics as Implicit Data Augmentation: A Depth-Decomposed View on Deep Neural Network Generalization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ruan, Tianyu, Gai, Kuo, Zhang, Shihua
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Analytical Solution of a Three-layer Network with a Matrix Exponential Activation Function
by: Gai, Kuo, et al.
Published: (2024)

OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attack
by: Gai, Kuo, et al.
Published: (2024)

Graph Generation with Spectral Geodesic Flow Matching
by: Huang, Xikun, et al.
Published: (2025)

Progressive Feedforward Collapse of ResNet Training
by: Wang, Sicong, et al.
Published: (2024)

Towards understanding how attention mechanism works in deep learning
by: Ruan, Tianyu, et al.
Published: (2024)

Feature Learning Dynamics in Infinite-Depth Neural Networks
by: Yao, Zihan, et al.
Published: (2025)

Decomposing the Depth Profile of Fine-Tuning
by: Billa, Jayadev
Published: (2026)

Explicit and Implicit Graduated Optimization in Deep Neural Networks
by: Sato, Naoki, et al.
Published: (2024)

On the Neural Feature Ansatz for Deep Neural Networks
by: Tansley, Edward, et al.
Published: (2025)

Efficient and Effective Implicit Dynamic Graph Neural Network
by: Zhong, Yongjian, et al.
Published: (2024)

Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks
by: Bai, Zhiwei, et al.
Published: (2022)

Depth-induced NTK: Bridging Over-parameterized Neural Networks and Deep Neural Kernels
by: Tian, Yong-Ming, et al.
Published: (2025)

Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data
by: Li, Yuxuan, et al.
Published: (2024)

Neural Collapse Dynamics: Depth, Activation, Regularisation, and Feature Norm Threshold
by: Rupa, Anamika Paul
Published: (2026)

Implicit Generative Prior for Bayesian Neural Networks
by: Liu, Yijia, et al.
Published: (2024)

Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data
by: Hong, Wanli, et al.
Published: (2024)

Dynamical Implicit Neural Representations
by: Park, Yesom, et al.
Published: (2025)

Masked Clinical Modelling: A Framework for Synthetic and Augmented Survival Data Generation
by: Kuo, Nicholas I-Hsien, et al.
Published: (2024)

Hierarchical Decomposed Dual-domain Deep Learning for Sparse-View CT Reconstruction
by: Han, Yoseob
Published: (2025)

Decomposing Global Feature Effects Based on Feature Interactions
by: Herbinger, Julia, et al.
Published: (2023)

Data-Augmented Deep Learning for Downhole Depth Sensing and Validation
by: Xiao, Si-Yu, et al.
Published: (2025)

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics
by: Chen, Yenho, et al.
Published: (2024)

Implicit Bias of Mirror Flow in Homogeneous Neural Networks: Sparse and Dense Feature Learning
by: Jacobs, Tom, et al.
Published: (2026)

Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
by: Li, Binghui, et al.
Published: (2024)

How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
by: Littwin, Etai, et al.
Published: (2024)

Implicit Regularization and Generalization in Overparameterized Neural Networks
by: Johannsen, Zeran
Published: (2026)

Training Neural Networks on Data Sources with Unknown Reliability
by: Capstick, Alexander, et al.
Published: (2022)

ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence
by: Mei, Wenjie, et al.
Published: (2024)

Data Diversity as Implicit Regularization: How Does Diversity Shape the Weight Space of Deep Neural Networks?
by: Ba, Yang, et al.
Published: (2024)

Spatiotemporal Implicit Neural Representation as a Generalized Traffic Data Learner
by: Nie, Tong, et al.
Published: (2024)

Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-Smoothing
by: Fu, Guoji, et al.
Published: (2023)

Homomorphism Expressivity of Spectral Invariant Graph Neural Networks
by: Gai, Jingchu, et al.
Published: (2025)

Depth, Not Data: An Analysis of Hessian Spectral Bifurcation
by: Deng, Shenyang, et al.
Published: (2026)

Multi-Epoch learning with Data Augmentation for Deep Click-Through Rate Prediction
by: Fan, Zhongxiang, et al.
Published: (2024)

Slicing Input Features to Accelerate Deep Learning: A Case Study with Graph Neural Networks
by: Xu, Zhengjia, et al.
Published: (2024)

Factorized Neural Implicit DMD for Parametric Dynamics
by: Chen, Siyuan, et al.
Published: (2026)

How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?
by: Lai, Kuo-Wei, et al.
Published: (2026)

Implicit Hypergraph Neural Network
by: Choudhuri, Akash, et al.
Published: (2025)

KAT-GNN: A Knowledge-Augmented Temporal Graph Neural Network for Risk Prediction in Electronic Health Records
by: Lin, Kun-Wei, et al.
Published: (2025)

Kernel Semi-Implicit Variational Inference
by: Cheng, Ziheng, et al.
Published: (2024)