Dan Schonfeld

Menghan Wang, Yuchen Guo, Duanfeng Zhang et al.

How to leverage large language model's superior capability in e-commerce recommendation has been a hot topic. In this paper, we propose LLM-PKG, an efficient approach that distills the knowledge of LLMs into product knowledge graph (PKG) and then applies PKG to provide explainable recommendations. Specifically, we first build PKG by feeding curated prompts to LLM, and then map LLM response to real enterprise products. To mitigate the risks associated with LLM hallucination, we employ rigorous evaluation and pruning methods to ensure the reliability and availability of the KG. Through an A/B test conducted on an e-commerce website, we demonstrate the effectiveness of LLM-PKG in driving user engagements and transactions significantly.

Chirag Agarwal, Shahin Khobahi, Arindam Bose et al.

The lack of interpretability in current deep learning models causes serious concerns as they are extensively used for various life-critical applications. Hence, it is of paramount importance to develop interpretable deep learning models. In this paper, we consider the problem of blind deconvolution and propose a novel model-aware deep architecture that allows for the recovery of both the blur kernel and the sharp image from the blurred image. In particular, we propose the Deep Unfolded Richardson-Lucy (Deep-URL) framework -- an interpretable deep-learning architecture that can be seen as an amalgamation of classical estimation technique and deep neural network, and consequently leads to improved performance. Our numerical investigations demonstrate significant improvement compared to state-of-the-art algorithms.

Chirag Agarwal, Anh Nguyen, Dan Schonfeld

Deep neural networks (DNNs) have achieved state-of-the-art results in various pattern recognition tasks. However, they perform poorly on out-of-distribution adversarial examples i.e. inputs that are specifically crafted by an adversary to cause DNNs to misbehave, questioning the security and reliability of applications. In this paper, we encourage DNN classifiers to learn more discriminative features by imposing a center loss in addition to the regular softmax cross-entropy loss. Intuitively, the center loss encourages DNNs to simultaneously learns a center for the deep features of each class, and minimize the distances between the intra-class deep features and their corresponding class centers. We hypothesize that minimizing distances between intra-class features and maximizing the distances between inter-class features at the same time would improve a classifier's robustness to adversarial examples. Our results on state-of-the-art architectures on MNIST, CIFAR-10, and CIFAR-100 confirmed that intuition and highlight the importance of discriminative features.

Chirag Agarwal, Bo Dong, Dan Schonfeld et al.

Deep Neural Networks(DNN) have excessively advanced the field of computer vision by achieving state of the art performance in various vision tasks. These results are not limited to the field of vision but can also be seen in speech recognition and machine translation tasks. Recently, DNNs are found to poorly fail when tested with samples that are crafted by making imperceptible changes to the original input images. This causes a gap between the validation and adversarial performance of a DNN. An effective and generalizable robustness metric for evaluating the performance of DNN on these adversarial inputs is still missing from the literature. In this paper, we propose Noise Sensitivity Score (NSS), a metric that quantifies the performance of a DNN on a specific input under different forms of fix-directional attacks. An insightful mathematical explanation is provided for deeply understanding the proposed metric. By leveraging the NSS, we also proposed a skewness based dataset robustness metric for evaluating a DNN's adversarial performance on a given dataset. Extensive experiments using widely used state of the art architectures along with popular classification datasets, such as MNIST, CIFAR-10, CIFAR-100, and ImageNet, are used to validate the effectiveness and generalization of our proposed metrics. Instead of simply measuring a DNN's adversarial robustness in the input domain, as previous works, the proposed NSS is built on top of insightful mathematical understanding of the adversarial attack and gives a more explicit explanation of the robustness.

Mehdi Sharifzadeh, Chirag Agarwal, Mohammed Aloraini et al.

This paper presents a novel approach to increase the performance bounds of image steganography under the criteria of minimizing distortion. The proposed approach utilizes a steganalysis convolutional neural network (CNN) framework to understand an image's model and embed in less detectable regions to preserve the model. In other word, the trained steganalysis CNN is used to calculate derivatives of the statistical model of an image with respect to embedding changes. The experimental results show that the proposed algorithm outperforms previous state-of-the-art methods in a wide range of low relative payloads when compared with HUGO, S-UNIWARD, and HILL by the state-of-the-art steganalysis.

Mehdi Sharifzadeh, Chirag Agarwal, Mahdi Salarian et al.

This paper presents two novel approaches to increase performance bounds of image steganography under the criteria of minimizing distortion. First, in order to efficiently use the images' capacities, we propose using parallel images in the embedding stage. The result is then used to prove sub-optimality of the message distribution technique used by all cost based algorithms including HUGO, S-UNIWARD, and HILL. Second, a new distribution approach is presented to further improve the security of these algorithms. Experiments show that this distribution method avoids embedding in smooth regions and thus achieves a better performance, measured by state-of-the-art steganalysis, when compared with the current used distribution.

Chirag Agarwal, Joe Klobusicky, Dan Schonfeld

We study a class of deep neural networks with networks that form a directed acyclic graph (DAG). For backpropagation defined by gradient descent with adaptive momentum, we show weights converge for a large class of nonlinear activation functions. The proof generalizes the results of Wu et al. (2008) who showed convergence for a feed forward network with one hidden layer. For an example of the effectiveness of DAG architectures, we describe an example of compression through an autoencoder, and compare against sequential feed forward networks under several metrics.

Shmuel Friedland, Qun Li, Dan Schonfeld

Compressive sensing (CS) has triggered enormous research activity since its first appearance. CS exploits the signal's sparsity or compressibility in a particular domain and integrates data compression and acquisition, thus allowing exact reconstruction through relatively few non-adaptive linear measurements. While conventional CS theory relies on data representation in the form of vectors, many data types in various applications such as color imaging, video sequences, and multi-sensor networks, are intrinsically represented by higher-order tensors. Application of CS to higher-order data representation is typically performed by conversion of the data to very long vectors that must be measured using very large sampling matrices, thus imposing a huge computational and memory burden. In this paper, we propose Generalized Tensor Compressive Sensing (GTCS)--a unified framework for compressive sensing of higher-order tensors which preserves the intrinsic structure of tensor data with reduced computational complexity at reconstruction. GTCS offers an efficient means for representation of multidimensional data by providing simultaneous acquisition and compression from all tensor modes. In addition, we propound two reconstruction procedures, a serial method (GTCS-S) and a parallelizable method (GTCS-P). We then compare the performance of the proposed method with Kronecker compressive sensing (KCS) and multi way compressive sensing (MWCS). We demonstrate experimentally that GTCS outperforms KCS and MWCS in terms of both reconstruction accuracy (within a range of compression ratios) and processing speed. The major disadvantage of our methods (and of MWCS as well), is that the compression ratios may be worse than that offered by KCS.

Liming Wang, Dan Schonfeld

Processing of symbolic sequences represented by mapping of symbolic data into numerical signals is commonly used in various applications. It is a particularly popular approach in genomic and proteomic sequence analysis. Numerous mappings of symbolic sequences have been proposed for various applications. It is unclear however whether the processing of symbolic data provides an artifact of the numerical mapping or is an inherent property of the symbolic data. This issue has been long ignored in the engineering and scientific literature. It is possible that many of the results obtained in symbolic signal processing could be a byproduct of the mapping and might not shed any light on the underlying properties embedded in the data. Moreover, in many applications, conflicting conclusions may arise due to the choice of the mapping used for numerical representation of symbolic data. In this paper, we present a novel framework for the analysis of the equivalence of the mappings used for numerical representation of symbolic data. We present strong and weak equivalence properties and rely on signal correlation to characterize equivalent mappings. We derive theoretical results which establish conditions for consistency among numerical mappings of symbolic data. Furthermore, we introduce an abstract mapping model for symbolic sequences and extend the notion of equivalence to an algebraic framework. Finally, we illustrate our theoretical results by application to DNA sequence analysis.