MetaSSD: Meta-Learned Self-Supervised Detection

TL;DR

MetaSSD introduces a meta-learning and self-supervised approach for symbol detection that adapts quickly to new channels with less supervision, outperforming traditional methods in noisy environments.

Contribution

The paper presents a novel meta-learning-based self-supervised symbol detector that adapts efficiently to new channels with minimal supervision, addressing limitations of previous supervised methods.

Findings

MetaSSD outperforms OFDM-MMSE with noisy channels.

MetaSSD achieves results comparable to BCJR.

Ablation studies confirm the importance of each component.

Abstract

Deep learning-based symbol detector gains increasing attention due to the simple algorithm design than the traditional model-based algorithms such as Viterbi and BCJR. The supervised learning framework is often employed to predict the input symbols, where training symbols are used to train the model. There are two major limitations in the supervised approaches: a) a model needs to be retrained from scratch when new train symbols come to adapt to a new channel status, and b) the length of the training symbols needs to be longer than a certain threshold to make the model generalize well on unseen symbols. To overcome these challenges, we propose a meta-learning-based self-supervised symbol detector named MetaSSD. Our contribution is two-fold: a) meta-learning helps the model adapt to a new channel environment based on experience with various meta-training environments, and b) self-supervised learning helps the model to use relatively less supervision than the previously suggested learning-based detectors. In experiments, MetaSSD outperforms OFDM-MMSE with noisy channel information and shows comparable results with BCJR. Further ablation studies show the necessity of each component in our framework.