SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networks

Generative AI & LLMs

Published: arXiv: 2509.22581v1

Authors

Jini Yang Beomseok Oh Seungryong Kim Sunok Kim

Abstract

Spiking neural networks (SNNs) have recently been attracting significant attention for their biological plausibility and energy efficiency, but semi-supervised learning (SSL) methods for SNN-based models remain underexplored compared to those for artificial neural networks (ANNs). In this paper, we introduce SpikeMatch, the first SSL framework for SNNs that leverages the temporal dynamics through the leakage factor of SNNs for diverse pseudo-labeling within a co-training framework. By utilizing agreement among multiple predictions from a single SNN, SpikeMatch generates reliable pseudo-labels from weakly-augmented unlabeled samples to train on strongly-augmented ones, effectively mitigating confirmation bias by capturing discriminative features with limited labels. Experiments show that SpikeMatch outperforms existing SSL methods adapted to SNN backbones across various standard benchmarks.

Paper Summary

Problem

The main problem this paper addresses is the challenge of semi-supervised learning (SSL) for spiking neural networks (SNNs). While SNNs have shown promise for their biological plausibility and energy efficiency, they require a lot of labeled data to train, which can be expensive and time-consuming to obtain. This makes it difficult to apply SNNs to real-world problems where labeled data is scarce.

Key Innovation

The key innovation of this paper is the introduction of SpikeMatch, the first SSL framework for SNNs that leverages the temporal dynamics of SNNs to generate diverse pseudo-labels. SpikeMatch uses a co-training framework that combines the agreement among multiple predictions from a single SNN to produce reliable pseudo-labels from weakly-augmented unlabeled samples.

Practical Impact

This research has practical implications for the development of SNNs for real-world applications. By enabling SSL for SNNs, SpikeMatch can help reduce the need for large amounts of labeled data, making it more feasible to apply SNNs to problems where labeled data is scarce. This can lead to more efficient and cost-effective development of AI models for various applications.

Analogy / Intuitive Explanation

Think of SpikeMatch like a team of multiple experts working together to make a decision. Each expert (SNN) makes a prediction, and the team (co-training framework) agrees on the final decision. This agreement-based pseudo-labeling approach helps to mitigate confirmation bias and enhance feature learning with limited labeled data. Just like how a team of experts can make more accurate decisions than a single expert, SpikeMatch can produce more reliable pseudo-labels than traditional SSL methods.

Paper Information

Categories:

cs.CV

Published Date:

arXiv ID:

2509.22581v1

Quick Actions

Back to Home