MAcPNN: Mutual Assisted Learning on Data Streams with Temporal Dependence

2026-03-09

AI Summary

This work proposes MAcPNN, a mutually assisted continual learning framework designed to address the challenges of concept drift, catastrophic forgetting, and inefficient knowledge sharing in edge devices processing streaming time-series data. MAcPNN introduces Vygotsky’s sociocultural theory of cognition into edge intelligence for the first time, enabling devices to dynamically request and evaluate knowledge assistance from peers on demand—without centralized coordination—whenever performance degrades. By integrating continual Progressive Neural Networks (cPNN), single-point prediction, and quantization techniques, the framework achieves efficient memory utilization and adaptive learning. Experimental results demonstrate that MAcPNN significantly improves model accuracy on both synthetic and real-world data streams while substantially reducing communication overhead and synchronization frequency.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Multiagent Systems: Multiagent Learning
• Intelligent Robots: Cognitive Robotics

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Social networks and social learning
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Internet of Things (IoT) Analytics often involves applying machine learning (ML) models on data streams. In such scenarios, traditional ML paradigms face obstacles related to continuous learning while dealing with concept drifts, temporal dependence, and avoiding forgetting. Moreover, in IoT, different edge devices build up a network. When learning models on those devices, connecting them could be useful in improving performance and reusing others' knowledge. This work proposes Mutual Assisted Learning, a learning paradigm grounded on Vygotsky's popular Sociocultural Theory of Cognitive Development. Each device is autonomous and does not need a central orchestrator. Whenever it degrades its performance due to a concept drift, it asks for assistance from others and decides whether their knowledge is useful for solving the new problem. This way, the number of connections is drastically reduced compared to the classical Federated Learning approaches, where the devices communicate at each training round. Every device is equipped with a Continuous Progressive Neural Network (cPNN) to handle the dynamic nature of data streams. We call this implementation Mutual Assisted cPNN (MAcPNN). To implement it, we allow cPNNs for single data point predictions and apply quantization to reduce the memory footprint. Experimental results prove the effectiveness of MAcPNN in boosting performance on synthetic and real data streams.

Problem

• concept drift
• temporal dependence
• catastrophic forgetting
• edge devices
• data streams

Innovation

• Mutual Assisted Learning
• Continuous Progressive Neural Network
• Concept Drift
• Edge Intelligence
• Data Streams