@article{mahdizadehaghdam_panahi_krim_dai_2019, title={Deep Dictionary Learning: A PARametric NETwork Approach}, volume={28}, ISSN={["1941-0042"]}, DOI={10.1109/TIP.2019.2914376}, abstractNote={Deep dictionary learning seeks multiple dictionaries at different image scales to capture complementary coherent characteristics. We propose a method for learning a hierarchy of synthesis dictionaries with an image classification goal. The dictionaries and classification parameters are trained by a classification objective, and the sparse features are extracted by reducing a reconstruction loss in each layer. The reconstruction objectives in some sense regularize the classification problem and inject source signal information in the extracted features. The performance of the proposed hierarchical method increases by adding more layers, which consequently makes this model easier to tune and adapt. The proposed algorithm furthermore shows a remarkably lower fooling rate in the presence of adversarial perturbation. The validation of the proposed approach is based on its classification performance using four benchmark datasets and is compared to a Convolutional Neural Network (CNN) of similar size.}, number={10}, journal={IEEE TRANSACTIONS ON IMAGE PROCESSING}, author={Mahdizadehaghdam, Shahin and Panahi, Ashkan and Krim, Hamid and Dai, Liyi}, year={2019}, month={Oct}, pages={4790–4802} }
 @article{mahdizadehaghdam_panahi_krim_2019, title={Sparse Generative Adversarial Network}, ISSN={["2473-9936"]}, DOI={10.1109/ICCVW.2019.00369}, abstractNote={We propose a new approach to Generative Adversarial Networks (GANs) to achieve an improved performance with additional robustness to its so-called and well-recognized mode collapse. We first proceed by mapping the desired data onto a frame-based space for a sparse representation to lift any limitation of small support features prior to learning the structure. To that end, we start by dividing an image into multiple patches and modifying the role of the generative network from producing an entire image, at once, to creating a sparse representation vector for each image patch. We synthesize an entire image by multiplying generated sparse representations to a pre-trained dictionary and assembling the resulting patches. This approach restricts the output of the generator to a particular structure, obtained by imposing a Union of Subspaces (UoS) model to the original training data, leading to more realistic images, while maintaining a desired diversity. To further regularize GANs in generating high-quality images and to avoid the notorious mode-collapse problem, we introduce a third player in GANs, called reconstructor. This player utilizes an auto-encoding scheme to ensure that first, the input-output relation in the generator is injective and second each real image corresponds to some input noise. We present a number of experiments, where the proposed algorithm shows a remarkably higher inception score compared to the equivalent conventional GANs.}, journal={2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW)}, author={Mahdizadehaghdam, Shahin and Panahi, Ashkan and Krim, Hamid}, year={2019}, pages={3063–3071} }
 @article{mahdizadehaghdam_wang_krim_dai_2016, title={Information Diffusion of Topic Propagation in Social Media}, volume={2}, ISSN={["2373-776X"]}, DOI={10.1109/tsipn.2016.2618324}, abstractNote={Real-world social and/or operational networks consist of agents with associated states, whose connectivity forms complex topologies. This complexity is further compounded by interconnected information layers, consisting, for instance, documents/resources of the agents which mutually share topical similarities. Our goal in this paper is to predict the specific states of the agents, as their observed resources evolve in time and get updated. The information diffusion among the agents and the publications themselves effectively result in a dynamic process which we capture by an interconnected system of networks (i.e., layered). More specifically, we use a notion of a supra-Laplacian matrix to address such a generalized diffusion of an interconnected network starting with the classical “graph Laplacian.” The auxiliary and external input update is modeled by a multidimensional Brownian process, yielding two contributions to the variations in the states of the agents: one that is due to the intrinsic interactions in the network system, and the other due to the external inputs or innovations. A variation on this theme, a priori knowledge of a fraction of the agents' states is shown to lead to a Kalman predictor problem. This helps us refine the predicted states exploiting the estimation error in the agents' states. Three real-world datasets are used to evaluate and validate the information diffusion process in this novel-layered network approach. Our results demonstrate a lower prediction error when using the interconnected network rather than the single connectivity layer between the agents. The prediction error is further improved by using the estimated diffusion connection and by applying the Kalman approach with partial observations.}, number={4}, journal={IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS}, author={Mahdizadehaghdam, Shahin and Wang, Han and Krim, Hamid and Dai, Liyi}, year={2016}, month={Dec}, pages={569–581} }