StreamFP: Learnable Fingerprint-guided Data Selection for Efficient Stream Learning

TL;DR

StreamFP introduces a learnable, fingerprint-guided data selection method that significantly improves efficiency and accuracy in stream learning by adaptively selecting data and updating buffers in dynamic environments.

Contribution

It presents a novel fingerprint-guided mechanism with learnable parameters for adaptive data selection in stream learning, outperforming existing methods.

Findings

Achieves accuracy improvements of up to 51.24% over baselines.

Increases training throughput by 4.6 times.

Effectively adapts to varying data arrival rates.

Abstract

Stream Learning (SL) requires models that can quickly adapt to continuously evolving data, posing significant challenges in both computational efficiency and learning accuracy. Effective data selection is critical in SL to ensure a balance between information retention and training efficiency. Traditional rule-based data selection methods struggle to accommodate the dynamic nature of streaming data, highlighting the necessity for innovative solutions that effectively address these challenges. Recent approaches to handling changing data distributions face challenges that limit their effectiveness in fast-paced environments. In response, we propose StreamFP, a novel approach that uniquely employs dynamic, learnable parameters called fingerprints to enhance data selection efficiency and adaptability in stream learning. StreamFP optimizes coreset selection through its unique fingerprint-guided mechanism for efficient training while ensuring robust buffer updates that adaptively respond to data dynamics, setting it apart from existing methods in stream learning. Experimental results demonstrate that StreamFP outperforms state-of-the-art methods by achieving accuracy improvements of 15.99%, 29.65%, and 51.24% compared to baseline models across varying data arrival rates, alongside a training throughput increase of 4.6x.