# Prospective Messaging: Learning in Networks with Communication Delays

arXiv: https://arxiv.org/abs/2407.05494 · HTML: https://mlsanity.com/paper/2407.05494/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 87 references that are in the map.
- First posted on arXiv 7 Jul 2024.

## Builds on (most cited first, 17 of 17)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Automatic differentiation in machine learning: a survey](https://mlsanity.com/paper/1502.05767/) (2015)
- [On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport](https://mlsanity.com/paper/1805.09545/) (2018)
- [Decoupled Neural Interfaces using Synthetic Gradients](https://mlsanity.com/paper/1608.05343/) (2016)
- [Asynchronous Stochastic Gradient Descent with Delay Compensation](https://mlsanity.com/paper/1609.08326/) (2016)
- [Predictive Coding: a Theoretical and Experimental Review](https://mlsanity.com/paper/2107.12979/) (2021)
- [Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs](https://mlsanity.com/paper/2206.00939/) (2022)
- [A Modern Primer on Processing in Memory](https://mlsanity.com/paper/2012.03112/) (2020)
- [Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons](https://mlsanity.com/paper/2110.14549/) (2021)
- [Deep Temporal Sigmoid Belief Networks for Sequence Modeling](https://mlsanity.com/paper/1509.07087/) (2015)
- [Axonal Delay As a Short-Term Memory for Feed Forward Deep Spiking Neural Networks](https://mlsanity.com/paper/2205.02115/) (2022)
- [Deep Neural Networks using a Single Neuron: Folded-in-Time Architecture using Feedback-Modulated Delay Loops](https://mlsanity.com/paper/2011.10115/) (2020)
- [DACOM: Learning Delay-Aware Communication for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2212.01619/) (2022)
- [Optoelectronic Intelligence](https://mlsanity.com/paper/2010.08690/) (2020)
- [Delay Learning Architectures for Memory and Classification](https://mlsanity.com/paper/1311.1294/) (2013)
- [Integration of continuous-time dynamics in a spiking neural network simulator](https://mlsanity.com/paper/1610.09990/) (2016)

## Abstract (arXiv)

Inter-neuron communication delays are ubiquitous in physically realized neural networks such as biological neural circuits and neuromorphic hardware. These delays have significant and often disruptive consequences on network dynamics during training and inference. It is therefore essential that communication delays be accounted for, both in computational models of biological neural networks and in large-scale neuromorphic systems. Nonetheless, communication delays have yet to be comprehensively addressed in either domain. In this paper, we first show that delays prevent state-of-the-art continuous-time neural networks called Latent Equilibrium (LE) networks from learning even simple tasks despite significant overparameterization. We then propose to compensate for communication delays by predicting future signals based on currently available ones. This conceptually straightforward approach, which we call prospective messaging (PM), uses only neuron-local information, and is flexible in terms of memory and computation requirements. We demonstrate that incorporating PM into delayed LE networks prevents reaction lags, and facilitates successful learning on Fourier synthesis and autoregressive video prediction tasks.