Targeted Fine-Tuning of DNN-Based Receivers via Influence Functions
This work addresses the challenge of adapting wireless receivers for specific cases, though it is incremental as it builds on existing methods like DeepRx and influence functions.
The paper tackled the problem of improving deep learning-based wireless receivers by using influence functions to identify key training samples for targeted fine-tuning, resulting in a more consistent reduction in bit error rate towards genie-aided performance compared to random fine-tuning in single-target scenarios.
We present the first use of influence functions for deep learning-based wireless receivers. Applied to DeepRx, a fully convolutional receiver, influence analysis reveals which training samples drive bit predictions, enabling targeted fine-tuning of poorly performing cases. We show that loss-relative influence with capacity-like binary cross-entropy loss and first-order updates on beneficial samples most consistently improves bit error rate toward genie-aided performance, outperforming random fine-tuning in single-target scenarios. Multi-target adaptation proved less effective, underscoring open challenges. Beyond experiments, we connect influence to self-influence corrections and propose a second-order, influence-aligned update strategy. Our results establish influence functions as both an interpretability tool and a basis for efficient receiver adaptation.