arXiv subjects

Dan Schonfeld

Publications and source records attributed to Dan Schonfeld.

12 recordsLinked to original sources

arXiv2024

Enabling Explainable Recommendation in E-commerce with LLM-powered Product Knowledge Graph

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.

cs.IR↗

arXiv2020

Convergence of backpropagation with momentum for network architectures with skip connections

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.

cs.CV↗

arXiv2019

Deep Radar Waveform Design for Efficient Automotive Radar Sensing

In radar systems, unimodular (or constant-modulus) waveform design plays an important role in achieving better clutter/interference rejection, as well as a more accurate estimation of the target parameters. The design of such sequences has been studied widely in the last few decades, with most design algorithms requiring sophisticated a priori knowledge of environmental parameters which may be difficult to obtain in real-time scenarios. In this paper, we propose a novel hybrid model-driven and data-driven architecture that adapts to the ever changing environment and allows for adaptive unimodular waveform design. In particular, the approach lays the groundwork for developing extremely low-cost waveform design and processing frameworks for radar systems deployed in autonomous vehicles. The proposed model-based deep architecture imitates a well-known unimodular signal design algorithm in its structure, and can quickly infer statistical information from the environment using the observed data. Our numerical experiments portray the advantages of using the proposed method for efficient radar waveform design in time-varying environments.

eess.SP↗

arXiv2019

A New Parallel Message-distribution Technique for Cost-based Steganography

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.

cs.MM↗

arXiv2019

Improving Adversarial Robustness by Encouraging Discriminative Features

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.

cs.CR↗

arXiv2018

An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks

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.

cs.CR↗

arXiv2017

Convolutional Neural Network Steganalysis's Application to Steganography

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.

cs.MM↗

arXiv2014

Two algorithms for compressed sensing of sparse tensors

Compressed sensing (CS) exploits the sparsity of a signal in order to integrate acquisition and compression. CS theory enables exact reconstruction of a sparse signal from relatively few linear measurements via a suitable nonlinear minimization process. Conventional CS theory relies on vectorial data representation, which results in good compression ratios at the expense of increased computational complexity. In applications involving color images, video sequences, and multi-sensor networks, the data is intrinsically of high-order, and thus more suitably represented in tensorial form. Standard applications of CS to higher-order data typically involve representation of the data as long vectors that are in turn measured using large sampling matrices, thus imposing a huge computational and memory burden. In this chapter, we introduce Generalized Tensor Compressed Sensing (GTCS)--a unified framework for compressed sensing of higher-order tensors which preserves the intrinsic structure of tensorial data with reduced computational complexity at reconstruction. We demonstrate that 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), both capable of recovering a tensor based on noiseless and noisy observations. We then compare the performance of the proposed methods with Kronecker compressed sensing (KCS) and multi-way compressed 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 achieved compression ratios may be worse than those offered by KCS.

cs.IT↗

arXiv2014

Compressive Sensing of Sparse Tensors

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.

cs.CV↗

arXiv2013

Message Error Analysis of Loopy Belief Propagation for the Sum-Product Algorithm

Belief propagation is known to perform extremely well in many practical statistical inference and learning problems using graphical models, even in the presence of multiple loops. The iterative use of belief propagation algorithm on loopy graphs is referred to as Loopy Belief Propagation (LBP). Various sufficient conditions for convergence of LBP have been presented; however, general necessary conditions for its convergence to a unique fixed point remain unknown. Because the approximation of beliefs to true marginal probabilities has been shown to relate to the convergence of LBP, several methods have been explored whose aim is to obtain distance bounds on beliefs when LBP fails to converge. In this paper, we derive uniform and non-uniform error bounds on messages, which are tighter than existing ones in literature, and use these bounds to derive sufficient conditions for the convergence of LBP in terms of the sum-product algorithm. We subsequently use these bounds to study the dynamic behavior of the sum-product algorithm, and analyze the relation between convergence of LBP and sparsity and walk-summability of graphical models. We finally use the bounds derived to investigate the accuracy of LBP, as well as the scheduling priority in asynchronous LBP.

cs.IT↗

arXiv2009

Two-Dimensional ARMA Modeling for Breast Cancer Detection and Classification

We propose a new model-based computer-aided diagnosis (CAD) system for tumor detection and classification (cancerous v.s. benign) in breast images. Specifically, we show that (x-ray, ultrasound and MRI) images can be accurately modeled by two-dimensional autoregressive-moving average (ARMA) random fields. We derive a two-stage Yule-Walker Least-Squares estimates of the model parameters, which are subsequently used as the basis for statistical inference and biophysical interpretation of the breast image. We use a k-means classifier to segment the breast image into three regions: healthy tissue, benign tumor, and cancerous tumor. Our simulation results on ultrasound breast images illustrate the power of the proposed approach.

cs.AI↗

arXiv2009

Mapping Equivalence for Symbolic Sequences: Theory and Applications

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.

cs.IT↗