Biologically Inspired Spiking Diffusion Model with Adaptive Lateral Selection Mechanism
Authors:
- Linghao FengLFLinghao Feng
- Dongcheng ZhaoDZDongcheng Zhao
- Sicheng ShenSSSicheng Shen
- Yi ZengYZYi Zeng
Preprint
Abstract
Lateral connection is a fundamental feature of biological neural circuits, facilitating local information processing and adaptive learning. In this work, we integrate lateral connections with a substructure selection network to develop a novel diffusion model based on spiking neural networks (SNNs). Unlike conventional artificial neural networks, SNNs employ an intrinsic spiking inner loop to process sequential binary spikes. We leverage this spiking inner loop alongside a lateral connection mechanism to iteratively refine the substructure selection network, enhancing model adaptability and expressivity. Specifically, we design a lateral connection framework comprising a learnable lateral matrix and a lateral mapping function, both implemented using spiking neurons, to dynamically update lateral connections. Through mathematical modeling, we establish that the proposed lateral update mechanism, under a well-defined local objective, aligns with biologically plausible synaptic plasticity principles. Extensive experiments validate the effectiveness of our approach, analyzing the role of substructure selection and lateral connection during training. Furthermore, quantitative comparisons demonstrate that our model consistently surpasses state-of-the-art SNN-based generative models across multiple benchmark datasets.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Time Cell Inspired Temporal Codebook in Spiking Neural Networks for Enhanced Image GenerationIEEE Transactions on Cognitive and Developmental Systems, 2026
- Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks2024
- Spiking generative adversarial network with attention scoring decodingNeural Networks, 2024
- An unsupervised STDP-based spiking neural network inspired by biologically plausible learning rules and connectionsNeural Networks, 2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Towards spike-based machine intelligence with neuromorphic computingNature, 2019
- Neural fields, spectral responses and lateral connectionsNeuroImage, 2011
- Contribution of feedforward, lateral and feedback connections to the classical receptive field center and extra-classical receptive field surround of primate V1 neurons2006
- Spike-Frequency Adaptation of a Generalized Leaky Integrate-and-Fire Model NeuronJournal of Computational Neuroscience, 2001
- Networks of spiking neurons: The third generation of neural network modelsNeural Networks, 1997