We consider the problem of compressing an information source when a correlated one is available as side information only at the decoder side, which is a special case of the distributed source coding problem in information theory. In particular, we consider a pair of stereo images, which have overlapping fields of view, and are captured by a synchronized and calibrated pair of cameras as correlated image sources. In previously proposed methods, the encoder transforms the input image to a latent representation using a deep neural network, and compresses the quantized latent representation losslessly using entropy coding. The decoder decodes the entropy-coded quantized latent representation, and reconstructs the input image using this representation and the available side information. In the proposed method, the decoder employs a cross-attention module to align the feature maps obtained from the received latent representation of the input image and a latent representation of the side information. We argue that aligning the correlated patches in the feature maps allows better utilization of the side information. We empirically demonstrate the competitiveness of the proposed algorithm on KITTI and Cityscape datasets of stereo image pairs. Our experimental results show that the proposed architecture is able to exploit the decoder-only side information in a more efficient manner compared to previous works.

We present a novel deep neural network (DNN) architecture for compressing an image when a correlated image is available as side information only at the decoder, a special case of the well-known distributed source coding (DSC) problem in information theory. In particular, we consider a pair of stereo images, which generally have high correlation with each other due to overlapping fields of view, and assume that one image of the pair is to be compressed and transmitted, while the other image is available only at the decoder. In the proposed architecture, the encoder maps the input image to a latent space, quantizes the latent representation, and compresses it using entropy coding. The decoder is trained to extract the common information between the input image and the correlated image, using only the latter. The received latent representation and the locally generated common information are passed through a decoder network to obtain an enhanced reconstruction of the input image. The common information provides a succinct representation of the relevant information at the receiver. We train and demonstrate the effectiveness of the proposed approach on the KITTI and Cityscape datasets of stereo image pairs. Our results show that the proposed architecture is capable of exploiting the decoder-only side information, and outperforms previous work on stereo image compression with decoder side information.

We consider a distributed computation problem over a multiple access channel (MAC), with N devices. It is known that over-the-air computation (OAC) can provide significant gains for this problem, but existing works are limited to the scenario with matched source and channel bandwidths. We propose OAC schemes for block-fading MACs that modulate the source to fit the available channel bandwidth in a wideband channel, while having channel state information (CSI) only at the transmitter or the receiver. Our results show that the proposed OAC scheme outperforms even ideal capacity-achieving digital schemes when the CSI is available only at the transmitter, and the distortion does not scale with the number of participating devices. We demonstrate the effectiveness of our proposed scheme in federated edge learning (FEEL), where OAC is used to aggregate model updates from the participating devices.

We consider the problem of secure distributed matrix computation (SDMC), where auserqueries a function of data matrices generated at distributedsourcenodes. We assume the availability of$N$honest but curious computation servers, which are connected to the sources, the user, and each other through orthogonal and reliable communication links. Our goal is to minimize the amount of data that must be transmitted from the sources to the servers, called theupload cost, while guaranteeing that no$T$colluding servers can learn any information about the source matrices, and the user cannot learn any information beyond the computation result. We first focus on secure distributed matrix multiplication (SDMM), considering two matrices, and propose a novel polynomial coding scheme using the properties of finite field discrete Fourier transform, which achieves an upload cost significantly lower than the existing results in the literature. We then generalize the proposed scheme to include straggler mitigation, and to the multiplication of multiple matrices while keeping the input matrices, the intermediate computation results, as well as the final result secure against any$T$colluding servers. We also consider a special case, called computation with own data, where the data matrices used for computation belong to the user. In this case, we drop the security requirement against the user, and show that the proposed scheme achieves the minimal upload cost. We then propose methods for performing other common matrix computations securely on distributed servers, including changing the parameters of secret sharing, matrix transpose, matrix exponentiation, solving a linear system, and matrix inversion, which are then used to show how arbitrary matrix polynomials can be computed securely on distributed servers using the proposed procedure.

Cache-aided content delivery is studied in a multi-server system with P servers and K users, each equipped with a local cache memory. In the delivery phase, each user connects randomly to any p out of P servers. Thanks to the availability of multiple servers, which model small-cell base stations (SBSs), demands can be satisfied with reduced storage capacity at each server and reduced delivery rate per server; however, this also leads to reduced multicasting opportunities compared to the single-server scenario. A joint storage and proactive caching scheme is proposed, which exploits coded storage across the servers, uncoded cache placement at the users, and coded delivery. The delivery latency is studied for both successive and parallel transmissions from the servers. It is shown that, with successive transmissions the achievable average delivery latency is comparable to the one achieved in the single-server scenario, while the gap between the two depends on p, the available redundancy across the servers, and can be reduced by increasing the storage capacity at the SBSs. The optimality of the proposed scheme with uncoded cache placement and MDS-coded server storage is also proved for successive transmissions.

A code construction and repair scheme for optimal functional regeneration of multiple node failures is presented, which is based on stitching together short MDS codes on carefully chosen sets of points lying on a linearized polynomial. The nodes are connected wirelessly, hence all transmissions by helper nodes during a repair round are available to all the nodes being repaired. The scheme is simple and practical because of low subpacketization, low I/O cost and low computational cost. Achievability of the minimum-bandwidth regenerating (MBR) point, as well as an interior point, on the optimal storage-repair bandwidth tradeoff curve is shown. The subspace properties derived in the paper provide insight into the general properties of functional regenerating codes.

Repair of multiple partially failed cache nodes is studied in a distributed wireless content caching system, where r out of a total of n cache nodes lose part of their cached data. Broadcast repair of failed cache contents at the network edge is studied; that is, the surviving cache nodes transmit broadcast messages to the failed ones, which are then used, together with the surviving data in their local cache memories, to recover the lost content. The trade-off between the storage capacity and the repair bandwidth is derived. It is shown that utilizing the broadcast nature of the wireless medium and the surviving cache contents at partially failed nodes significantly reduces the required repair bandwidth per node.

Cache-aided content delivery is studied in a multi-server system with P servers and K users, each equipped with a local cache memory. In the delivery phase, each user connects randomly to any ρ out of P servers. Thanks to the availability of multiple servers, which model small base stations with limited storage capacity, user demands can be satisfied with reduced storage capacity at each server and reduced delivery rate per server; however, this also leads to reduced multicasting opportunities compared to a single server serving all the users simultaneously. A joint storage and proactive caching scheme is proposed, which exploits coded storage across the servers, uncoded cache placement at the users, and coded delivery. The delivery latency is studied for both successive and simultaneous transmission from the servers. It is shown that, with successive transmission the achievable average delivery latency is comparable to that achieved by a single server, while the gap between the two depends on ρ, the available redundancy across servers, and can be reduced by increasing the storage capacity at the SBSs.