Year: 2026
Type: conference-paper
Abstract: 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 ℓ-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.
Institutions: Nokia (Finland), University of Eastern Finland
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4414742191
FWCI:
Cites:
Cited by:
Related to: