mlsanityData to 14 Oct 2026

Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning

arXiv 2405.16851 ↗First posted 27 May 2024cs.NE cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Spiking neural networks (SNNs) are investigated as biologically inspired models of neural computation, distinguished by their computational capability and energy efficiency due to precise spiking times and sparse spikes with event-driven computation. A significant question is how SNNs can emulate human-like graph-based reasoning of concepts and relations, especially leveraging the temporal domain optimally. This paper reveals that SNNs, when amalgamated with synaptic delay and temporal coding, are proficient in executing (knowledge) graph reasoning. It is elucidated that spiking time can function as an additional dimension to encode relation properties via a neural-generalized path formulation. Empirical results highlight the efficacy of temporal delay in relation processing and showcase exemplary performance in diverse graph reasoning tasks. The spiking model is theoretically estimated to achieve 20× energy savings compared to non-spiking counterparts, deepening insights into the capabilities and potential of biologically inspired SNNs for efficient reasoning. The code is available at https://github.com/pkuxmq/GRSNN.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 35 of its 66 references that are in the map. First posted on arXiv 27 May 2024.

Builds on

35 of 66 references.

References · 35

  1. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  2. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  3. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  4. 2016Variational Graph Auto-Encoderscited by 1,382
  5. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  6. 2016Complex Embeddings for Simple Link Predictioncited by 902
  7. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
  8. 2018Link Prediction Based on Graph Neural Networkscited by 832
  9. 2017Convolutional 2D Knowledge Graph Embeddingscited by 730
  10. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 396
  11. 2017A simple neural network module for relational reasoningcited by 346
  12. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 345
23 more
  1. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 275
  2. 2015A Review of Relational Machine Learning for Knowledge Graphscited by 265
  3. 2019Inductive Relation Prediction by Subgraph Reasoningcited by 239
  4. 2018Hyperspherical Variational Auto-Encoderscited by 189
  5. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 181
  6. 2019DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphscited by 175
  7. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 117
  8. 2021Accurate and efficient time-domain classification with adaptive spiking recurrent neural networkscited by 115
  9. 2022Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representationcited by 89
  10. 2016Supervised learning based on temporal coding in spiking neural networkscited by 76
  11. 2023Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacingscited by 50
  12. 2019Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performancecited by 46
  13. 2019Temporal Coding in Spiking Neural Networks with Alpha Synaptic Function: Learning with Backpropagationcited by 45
  14. 2021Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium Statecited by 40
  15. 2021Link Prediction with Persistent Homology: An Interactive Viewcited by 37
  16. 2022Spiking Graph Convolutional Networkscited by 27
  17. 2022Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networkscited by 24
  18. 2020LowFER: Low-rank Bilinear Pooling for Link Predictioncited by 20
  19. 2021SpikE: spike-based embeddings for multi-relational graph datacited by 9
  20. 2023Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principlescited by 8
  21. 2022Relational representation learning with spike trainscited by 4
  22. 2022Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attentioncited by 3
  23. 2022Brain-inspired Graph Spiking Neural Networks for Commonsense Knowledge Representation and Reasoningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2026Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiencycited by 3
  2. 2025Edge Intelligence with Spiking Neural Networkscited by 2
  3. 2025FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learningcited by 1
  4. 2026ChronoSpike: An Adaptive Spiking Graph Neural Network for Dynamic Graphscited by 1
  5. 2026Congestion-Aware Dynamic Axonal Delay for Spiking Neural Networkscited by 1