Privacy-Preserving Active Learning for sustainable aquaculture monitoring systems for extreme data sparsity scenarios

说明与用途

结合多样性正则化的主动学习、DP‑SGD和代理式编排的管道，在极端稀缺数据和边缘计算环境下，将所需标签减少约35%，同时保持准确性并提供差分隐私保障。

问题

Only a handful of labeled sensor readings were available from 40 deployed ESP32 water‑quality sensors, while the rest were miscalibrated, destroyed, or unlabeled, creating extreme data sparsity and privacy‑sensitive telemetry.

结果

The pipeline reduced required labels by ~35% while maintaining F1 performance and providing formal differential privacy guarantees in an extreme sparsity, edge‑only setting.

工作流

• Deploy ESP32 sensors with local 1D convolutional encoder to generate 32‑dim embeddings
• Use uncertainty sampling with diversity regularization to select unlabeled points for labeling
• Apply DP‑SGD with calibrated Gaussian noise during training
• Federate model updates from edge devices while accounting for privacy budget
• Run an agentic scheduler that monitors drift, budget, and decides next actions

证据

Out of 40 sensors deployed across six ponds, only 11 returned labeled, trustworthy readings after the first month.

来源

With lambda_div=0.5, the model reached the same F1 score with roughly 35% fewer labels than pure entropy sampling.

来源

DP‑SGD: clip per‑sample gradients, then add Gaussian noise calibrated to the clipping norm.

来源