Copertina

Not All Timesteps Matter Equally: Selective Alignment Knowledge Distillation for Spiking Neural Networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sun, Kai, Duan, Peibo, Huang, Yongsheng, Zhang, Guowei, Smith, Benjamin, Gong, Nanxu, Kuhlmann, Levin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ILIF: Temporal Inhibitory Leaky Integrate-and-Fire Neuron for Overactivation in Spiking Neural Networks
di: Sun, Kai, et al.
Pubblicazione: (2025)

CogniSNN: Enabling Neuron-Expandability, Pathway-Reusability, and Dynamic-Configurability with Random Graph Architectures in Spiking Neural Networks
di: Huang, Yongsheng, et al.
Pubblicazione: (2025)

A Distillation-based Future-aware Graph Neural Network for Stock Trend Prediction
di: Liu, Zhipeng, et al.
Pubblicazione: (2025)

CogniSNN: An Exploration to Random Graph Architecture based Spiking Neural Networks with Enhanced Depth-Scalability and Path-Plasticity
di: Huang, Yongsheng, et al.
Pubblicazione: (2025)

Not All Instances Are Equally Valuable: Towards Influence-Weighted Dataset Distillation
di: Deng, Qiyan, et al.
Pubblicazione: (2025)

MorphSNN: Adaptive Graph Diffusion and Structural Plasticity for Spiking Neural Networks
di: Huang, Yongsheng, et al.
Pubblicazione: (2026)

Cross Knowledge Distillation between Artificial and Spiking Neural Networks
di: Ye, Shuhan, et al.
Pubblicazione: (2025)

Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation
di: Wang, Shaobo, et al.
Pubblicazione: (2024)

SDSNN: A Single-Timestep Spiking Neural Network with Self-Dropping Neuron and Bayesian Optimization
di: Xu, Changqing, et al.
Pubblicazione: (2025)

Head-Tail-Aware KL Divergence in Knowledge Distillation for Spiking Neural Networks
di: Zhang, Tianqing, et al.
Pubblicazione: (2025)

Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment
di: Yu, Chengting, et al.
Pubblicazione: (2025)

Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation
di: Kang, Donghwa, et al.
Pubblicazione: (2025)

CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate
di: Sun, Yiliu, et al.
Pubblicazione: (2025)

Not All Explanations for Deep Learning Phenomena Are Equally Valuable
di: Jeffares, Alan, et al.
Pubblicazione: (2025)

TopSpark: A Timestep Optimization Methodology for Energy-Efficient Spiking Neural Networks on Autonomous Mobile Agents
di: Putra, Rachmad Vidya Wicaksana, et al.
Pubblicazione: (2023)

Efficient Speech Command Recognition Leveraging Spiking Neural Network and Curriculum Learning-based Knowledge Distillation
di: Wang, Jiaqi, et al.
Pubblicazione: (2024)

Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing
di: He, Jinmin, et al.
Pubblicazione: (2023)

Bridging the Domain Gap in Equation Distillation with Reinforcement Feedback
di: Ying, Wangyang, et al.
Pubblicazione: (2025)

AGHINT: Attribute-Guided Representation Learning on Heterogeneous Information Networks with Transformer
di: Yuan, Jinhui, et al.
Pubblicazione: (2024)

DisMS-TS: Eliminating Redundant Multi-Scale Features for Time Series Classification
di: Liu, Zhipeng, et al.
Pubblicazione: (2025)

Agentic Feature Augmentation: Unifying Selection and Generation with Teaming, Planning, and Memories
di: Gong, Nanxu, et al.
Pubblicazione: (2025)

The Disappearance of Timestep Embedding in Modern Time-Dependent Neural Networks
di: Kim, Bum Jun, et al.
Pubblicazione: (2024)

NCT-CRC-HE: Not All Histopathological Datasets Are Equally Useful
di: Ignatov, Andrey, et al.
Pubblicazione: (2024)

Target-Driven Distillation: Consistency Distillation with Target Timestep Selection and Decoupled Guidance
di: Wang, Cunzheng, et al.
Pubblicazione: (2024)

Data-Efficient Symbolic Regression via Foundation Model Distillation
di: Ying, Wangyang, et al.
Pubblicazione: (2025)

Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine Translation
di: Jin, Heegon, et al.
Pubblicazione: (2024)

Equally Critical: Samples, Targets, and Their Mappings in Datasets
di: Yang, Runkang, et al.
Pubblicazione: (2025)

Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models
di: Ye, Zekai, et al.
Pubblicazione: (2026)

Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning
di: Jali, Neharika, et al.
Pubblicazione: (2026)

Reinforcement Learning-based Sequential Route Recommendation for System-Optimal Traffic Assignment
di: Wang, Leizhen, et al.
Pubblicazione: (2025)

Training Spiking Neural Networks via Augmented Direct Feedback Alignment
di: Zhang, Yongbo, et al.
Pubblicazione: (2024)

Rapfi: Distilling Efficient Neural Network for the Game of Gomoku
di: Jin, Zhanggen, et al.
Pubblicazione: (2025)

Fully Spiking Neural Network for Legged Robots
di: Jiang, Xiaoyang, et al.
Pubblicazione: (2023)

A Functional Perspective on Knowledge Distillation in Neural Networks
di: Mason-Williams, Israel, et al.
Pubblicazione: (2025)

Online Adversarial Knowledge Distillation for Graph Neural Networks
di: Wang, Can, et al.
Pubblicazione: (2021)

Learning with Spike Synchrony in Spiking Neural Networks
di: Tian, Yuchen, et al.
Pubblicazione: (2025)

BiSpikCLM: A Spiking Language Model integrating Softmax-Free Spiking Attention and Spike-Aware Alignment Distillation
di: Guo, Sihang, et al.
Pubblicazione: (2026)

Temporal Information Reconstruction and Non-Aligned Residual in Spiking Neural Networks for Speech Classification
di: Zhang, Qi, et al.
Pubblicazione: (2024)

Activation-wise Propagation: A One-Timestep Strategy for Spiking Neural Networks
di: Song, Jian, et al.
Pubblicazione: (2025)

Hyperdimensional Decoding of Spiking Neural Networks
di: Kinavuidi, Cedrick, et al.
Pubblicazione: (2025)