Imagen de Portada

Pushing the Limits of Distillation-Based Continual Learning via Classifier-Proximal Lightweight Plugins

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Zhiming, Xu, Baile, Zhao, Jian, Shen, Furao, Yang, Suorong
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards Realistic Class-Incremental Learning with Free-Flow Increments
por: Xu, Zhiming, et al.
Publicado: (2026)

Dual Prototypes for Adaptive Pre-Trained Model in Class-Incremental Learning
por: Xu, Zhiming, et al.
Publicado: (2024)

RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment
por: Yang, Suorong, et al.
Publicado: (2025)

Physics-inspired Energy Transition Neural Network for Sequence Learning
por: Wu, Zhou, et al.
Publicado: (2025)

Data Agent: Learning to Select Data via End-to-End Dynamic Optimization
por: Yang, Suorong, et al.
Publicado: (2026)

Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning
por: Yang, Suorong, et al.
Publicado: (2025)

When Dynamic Data Selection Meets Data Augmentation
por: Yang, Suorong, et al.
Publicado: (2025)

EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classification
por: Yang, Suorong, et al.
Publicado: (2024)

Enhancing Epidemic Forecasting: Evaluating the Role of Mobility Data and Graph Convolutional Networks
por: Guo, Suhan, et al.
Publicado: (2025)

Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental Learning
por: Yi, Huiyu, et al.
Publicado: (2026)

Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training
por: Yang, Suorong, et al.
Publicado: (2026)

ConceptFlow: Hierarchical and Fine-grained Concept-Based Explanation for Convolutional Neural Networks
por: Mu, Xinyu, et al.
Publicado: (2025)

T-LLM: Teaching Large Language Models to Forecast Time Series via Temporal Distillation
por: Guo, Suhan, et al.
Publicado: (2026)

AffineLens: Capturing the Continuous Piecewise Affine Functions of Neural Networks
por: Wei, Yi, et al.
Publicado: (2026)

On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation
por: Yang, Suorong, et al.
Publicado: (2025)

Structure-Level Disentangled Diffusion for Few-Shot Chinese Font Generation
por: Li, Jie, et al.
Publicado: (2026)

Region Seeding via Pre-Activation Regularization: A Geometric View of Piecewise Affine Neural Networks
por: Wei, Yi, et al.
Publicado: (2026)

SPAT: Sensitivity-based Multihead-attention Pruning on Time Series Forecasting Models
por: Guo, Suhan, et al.
Publicado: (2025)

Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning
por: Hao, Chenjie, et al.
Publicado: (2025)

Multiple Queries with Multiple Keys: A Precise Prompt Matching Paradigm for Prompt-based Continual Learning
por: Tu, Dunwei, et al.
Publicado: (2025)

Multi-Scale Dilated Convolution Network for Long-Term Time Series Forecasting
por: Li, Feifei, et al.
Publicado: (2024)

Continuous Limits of Coupled Flows in Representation Learning
por: Li, Zilin, et al.
Publicado: (2026)

RAM: Replace Attention with MLP for Efficient Multivariate Time Series Forecasting
por: Guo, Suhan, et al.
Publicado: (2024)

Optimizing Parking Space Classification: Distilling Ensembles into Lightweight Classifiers
por: Alves, Paulo Luza, et al.
Publicado: (2024)

IPF-RDA: An Information-Preserving Framework for Robust Data Augmentation
por: Yang, Suorong, et al.
Publicado: (2025)

LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation
por: Song, Siqing, et al.
Publicado: (2026)

Explaining Model Overfitting in CNNs via GMM Clustering
por: Dou, Hui, et al.
Publicado: (2024)

AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation
por: Yang, Suorong, et al.
Publicado: (2024)

Server-Proximal Aggregation for Federated Domain-Incremental Learning under Partial Participation: Task-Uniform Convergence and Backward Transfer
por: Xu, Longtao, et al.
Publicado: (2026)

Dynamic Participation in Federated Learning: Benchmarks and a Knowledge Pool Plugin
por: Lee, Ming-Lun, et al.
Publicado: (2025)

Tripartite-GraphRAG via Plugin Ontologies
por: Banf, Michael, et al.
Publicado: (2025)

Pushing the Limits of Inverse Lithography with Generative Reinforcement Learning
por: Yang, Haoyu, et al.
Publicado: (2026)

Proximal Policy Distillation
por: Spigler, Giacomo
Publicado: (2024)

Pushing the Limits of Large Language Model Quantization via the Linearity Theorem
por: Malinovskii, Vladimir, et al.
Publicado: (2024)

Generalist Graph Anomaly Detection via Prototype-Based Distillation
por: Xu, Yiming, et al.
Publicado: (2026)

GeoPTH: A Lightweight Approach to Category-Based Trajectory Retrieval via Geometric Prototype Trajectory Hashing
por: Xu, Yang, et al.
Publicado: (2025)

Low-redundancy Distillation for Continual Learning
por: Liu, RuiQi, et al.
Publicado: (2023)

Distillation-Guided Structural Transfer for Continual Learning Beyond Sparse Distributed Memory
por: Xue, Huiyan, et al.
Publicado: (2025)

Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning
por: Yoo, Jason, et al.
Publicado: (2024)

UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment
por: Zeng, Kaipeng, et al.
Publicado: (2024)