skip to main content


Title: Contrastive learning with self-reconstruction for channel-resilient modulation classification
Despite the substantial success of deep learning for modulation classification, models trained on a specific transmitter configuration and channel model often fail to generalize well to other scenarios with different transmitter configurations, wireless fading channels, or receiver impairments such as clock offset. This paper proposes Contrastive Learning with Self- Reconstruction called CLSR-AMC to learn good representations of signals resilient to channel changes. While contrastive loss focuses on the differences between individual modulations, the reconstruction loss captures representative features of the signal. Additionally, we develop three data augmentation operators to emulate the impact of channel and hardware impairments without exhaustive modeling of different channel profiles. We perform extensive experimentation with commonly used datasets. We show that CLSR-AMC outperforms its counterpart based on contrastive learning for the same amount of labeled data by significant average accuracy gains of 24.29%, 17.01%, and 15.97% in Additive White Gaussian Noise (AWGN), Rayleigh+AWGN, and Rician+AWGN channels, respectively.  more » « less
Award ID(s):
2132700
PAR ID:
10428343
Author(s) / Creator(s):
Date Published:
Journal Name:
IEEE International Conference on Computer Communications (IEEE INFOCOM)
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. The accurate identification of wireless devices is critical for enabling automated network access monitoring and authenticated data communication in large-scale networks; e.g., IoT networks. RF fingerprinting has emerged as a potential solution for device identification by leveraging the transmitter unique manufacturing impairments of the RF components. Although deep learning is proven efficient in classifying devices based on the hardware impairments, trained models perform poorly due to channel variations. That is, although training and testing neural networks using data generated during the same period achieve reliable classification, testing them on data generated at different times degrades the accuracy substantially. To the best of our knowledge, we are the first to propose to leverage MIMO capabilities to mitigate the channel effect and provide a channelresilient device classification. For the proposed technique we show that, for Rayleigh channels, blind partial channel estimation enabled by MIMO increases the testing accuracy by up to 40% when the models are trained and tested over the same channel, and by up to 60% when the models are tested on a channel that is different from that used for training. 
    more » « less
  2. Previously, dynamic-assignment Blahut-Arimoto (DAB) was used to find capacity-achieving probability mass functions (PMFs) for binomial channels and molecular channels. As it turns out, DAB can efficiently identify capacity-achieving PMFs for a wide variety of channels. This paper applies DAB to power-constrained (PC) additive white Gaussian Noise (AWGN) Channels and amplitude-constrained (AC) AWGN Channels.This paper modifies DAB to include a power constraint and finds low-cardinality PMFs that approach capacity on PC-AWGN Channels. While a continuous Gaussian PDF is well-known to be capacity-achieving on the PC-AWGN channel, DAB identifies low-cardinality PMFs within 0.01 bits of the mutual information provided by a Gaussian PDF. Recall the results of Ozarow and Wyner requiring a constellation cardinality of ⌈2 ^ (C+1) ⌉ to approach capacity C to within the asymptotic shaping loss of 1.53 dB at high SNR. PMF's found by DAB approach capacity with essentially no shaping loss with cardinality less than 2 ^ (C+1.2) . As expected, DAB's numerical approach identifies PMFs with better mutual information vs. SNR performance than the analytical approaches to finite-support constellations examined by Wu and Verdu. This paper also uses DAB to find capacity-achieving PMFs with small cardinality support sets for AC-AWGN Channels. The resulting evolution of capacity-achieving PMFs as a function of SNR is consistent with the approximate cardinality transition points of Sharma and Shamai. 
    more » « less
  3. Low overhead channel estimation based on compressive sensing (CS) has been widely investigated for hybrid wideband millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems. The channel sparsifying dictionaries used in prior work are built from ideal array response vectors evaluated on discrete angles of arrival/departure. In addition, these dictionaries are assumed to be the same for all subcarriers, without considering the impacts of hardware impairments and beam squint. In this manuscript, we derive a general channel and signal model that explicitly incorporates the impacts of hardware impairments, practical pulse shaping functions, and beam squint, overcoming the limitations of mmWave MIMO channel and signal models commonly used in previous work. Then, we propose a dictionary learning (DL) algorithm to obtain the sparsifying dictionaries embedding hardware impairments, by considering the effect of beam squint without introducing it into the learning process. We also design a novel CS channel estimation algorithm under beam squint and hardware impairments, where the channel structures at different subcarriers are exploited to enable channel parameter estimation with low complexity and high accuracy. Numerical results demonstrate the effectiveness of the proposed DL and channel estimation strategy when applied to realistic mmWave channels. 
    more » « less
  4. null (Ed.)
    The fading broadcast channel (BC) with additive white Gaussian noise (AWGN) channel, channel output feedback (COF) and channel state information (CSI) is considered. Perfect CSI is available at the receivers, and unit delayed CSI along with COF at the transmitter. Under the assumption of memoryless fading, a posterior matching scheme that incorporates the additional CSI feedback into the coding scheme is presented. With COF, the achievable rates depend on the joint distribution of the fading process. Numerical examples show that the capacity region of two-user fading AWGN-BC is enlarged by COF. The coding scheme is however suboptimal since some parts of the achievable rate region are outperformed by superposition coding without COF. 
    more » « less
  5. null (Ed.)
    In this paper, we introduce a framework for Joint Source-Channel Coding of distributed Gaussian sources over a multiple access AWGN channel. Although there are prior works that have studied this, they either strongly rely on intuition to design encoders and decoder or require the knowledge of the complete joint distribution of all the distributed sources. Our system overcomes this. We model our system as a Variational Autoencoder and leverage insight provided by this connection to propose a crucial regularization mechanism for learning. This allows us to beat the state of the art by improving the signal reconstruction quality by almost 1dB for certain configurations. The end-to-end learned system is also found to be robust to channel condition variations of ±5dB and shows a drop in signal reconstruction quality by at most 1dB. Finally, we propose a novel lower bound on the optimal distortion in signal reconstruction and empirically showcase the tightness of the bound in comparison with the existing bound. 
    more » « less