A Graph Is Worth 1bit Spikes When Graph Contrastive Learning Meets Spiking Neural Networks
ASecurity**arXiv ID:** 2305.19306 **Authors:** Jintang Li, Huizhe Zhang, Ruofan Wu, Zulun Zhu, Baokun Wang, Changhua Meng, Zibin Zheng, Liang Chen **Published:** 2023-05-30T16:03:11Z **Abstract:** While contrastive self-supervised learning has become the de-facto learning paradigm for graph neural networks, the pursuit of higher task accuracy requires a larger hidden dimensionality to learn informative and discriminative full-precision representations, raising concerns about computation, memory footpr...
- 3 stars
- 0 votes
- 0 copies
- 3 views
- Added September 11, 2026
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill a-graph-is-worth-1bit-spikes-when-graph-contrastive-learning-meets-spiking-neural-networks --agent claude-codeAre you the author of A Graph Is Worth 1bit Spikes When Graph Contrastive Learning Meets Spiking Neural Networks?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-a-graph-is-worth-1bit-spikes-when-graph-contrastiv)# A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
**arXiv ID:** 2305.19306
**Authors:** Jintang Li, Huizhe Zhang, Ruofan Wu, Zulun Zhu, Baokun Wang, Changhua Meng, Zibin Zheng, Liang Chen
**Published:** 2023-05-30T16:03:11Z
**Abstract:**
While contrastive self-supervised learning has become the de-facto learning paradigm for graph neural networks, the pursuit of higher task accuracy requires a larger hidden dimensionality to learn informative and discriminative full-precision representations, raising concerns about computation, memory footprint, and energy consumption burden (largely overlooked) for real-world applications. This work explores a promising direction for graph contrastive learning (GCL) with spiking neural networks (SNNs), which leverage sparse and binary characteristics to learn more biologically plausible and compact representations. We propose SpikeGCL, a novel GCL framework to learn binarized 1-bit representations for graphs, making balanced trade-offs between efficiency and performance. We provide theoretical guarantees to demonstrate that SpikeGCL has comparable expressiveness with its full-precision counterparts. Experimental results demonstrate that, with nearly 32x representation storage compression, SpikeGCL is either comparable to or outperforms many fancy state-of-the-art supervised and self-supervised methods across several graph benchmarks.
## Skill Description
This skill is generated from the arXiv paper: A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks (2305.19306).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:2305.19306](http://arxiv.org/abs/2305.19306v2)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.