# MAcPNN: Mutual Assisted Learning on Data Streams with Temporal Dependence

arXiv: https://arxiv.org/abs/2603.08972 · HTML: https://mlsanity.com/paper/2603.08972/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 32 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges](https://mlsanity.com/paper/1907.00182/) (2019)
- [Peer-to-peer Federated Learning on Graphs](https://mlsanity.com/paper/1901.11173/) (2019)
- [Asynchronous Federated Learning for Sensor Data with Concept Drift](https://mlsanity.com/paper/2109.00151/) (2021)
- [Continual Learning with Gated Incremental Memories for sequential data processing](https://mlsanity.com/paper/2004.04077/) (2020)
- [cPNN: Continuous Progressive Neural Networks for Evolving Streaming Time Series](https://mlsanity.com/paper/2603.03040/) (2026)

## Abstract (arXiv)

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.