{"ID":2887254,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.01646","arxiv_id":"2508.01646","title":"SPARTA: Advancing Sparse Attention in Spiking Neural Networks via Spike-Timing-Based Prioritization","abstract":"Current Spiking Neural Networks (SNNs) underutilize the temporal dynamics inherent in spike-based processing, relying primarily on rate coding while overlooking precise timing information that provides rich computational cues. We propose SPARTA (Spiking Priority Attention with Resource-Adaptive Temporal Allocation), a framework that leverages heterogeneous neuron dynamics and spike-timing information to enable efficient sparse attention. SPARTA prioritizes tokens based on temporal cues, including firing patterns, spike timing, and inter-spike intervals, achieving 65.4% sparsity through competitive gating. By selecting only the most salient tokens, SPARTA reduces attention complexity from O(N^2) to O(K^2) with k \u003c\u003c n, while maintaining high accuracy. Our method achieves state-of-the-art performance on DVS-Gesture (98.78%) and competitive results on CIFAR10-DVS (83.06%) and CIFAR-10 (95.3%), demonstrating that exploiting spike timing dynamics improves both computational efficiency and accuracy.","short_abstract":"Current Spiking Neural Networks (SNNs) underutilize the temporal dynamics inherent in spike-based processing, relying primarily on rate coding while overlooking precise timing information that provides rich computational cues. We propose SPARTA (Spiking Priority Attention with Resource-Adaptive Temporal Allocation), a...","url_abs":"https://arxiv.org/abs/2508.01646","url_pdf":"https://arxiv.org/pdf/2508.01646v2","authors":"[\"Minsuk Jang\",\"Changick Kim\"]","published":"2025-08-03T08:11:33Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.NE\"]","methods":"[]","has_code":false}