arXiv subjects

Rishabh Gupta

Publications and source records attributed to Rishabh Gupta.

54 records · Page 3Linked to original sources

arXiv2022

A Differential Approach for Data and Classification Service based Privacy-Preserving Machine Learning Model in Cloud Environment

The massive upsurge in computational and storage has driven the local data and machine learning applications to the cloud environment. The owners may not fully trust the cloud environment as it is managed by third parties. However, maintaining privacy while sharing data and the classifier with several stakeholders is a critical challenge. This paper proposes a novel model based on differential privacy and machine learning approaches that enable multiple owners to share their data for utilization and the classifier to render classification services for users in the cloud environment. To process owners data and classifier, the model specifies a communication protocol among various untrustworthy parties. The proposed model also provides a robust mechanism to preserve the privacy of data and the classifier. The experiments are conducted for a Naive Bayes classifier over numerous datasets to compute the proposed model efficiency. The achieved results demonstrate that the proposed model has high accuracy, precision, recall, and F1-score up to 94%, 95%, 94%, and 94%, and improvement up to 16.95%, 20.16%, 16.95%, and 23.33%, respectively, compared with state-of-the-art works.

cs.CR↗

arXiv2022

A Privacy-Preserving Outsourced Data Model in Cloud Environment

Nowadays, more and more machine learning applications, such as medical diagnosis, online fraud detection, email spam filtering, etc., services are provided by cloud computing. The cloud service provider collects the data from the various owners to train or classify the machine learning system in the cloud environment. However, multiple data owners may not entirely rely on the cloud platform that a third party engages. Therefore, data security and privacy problems are among the critical hindrances to using machine learning tools, particularly with multiple data owners. In addition, unauthorized entities can detect the statistical input data and infer the machine learning model parameters. Therefore, a privacy-preserving model is proposed, which protects the privacy of the data without compromising machine learning efficiency. In order to protect the data of data owners, the epsilon-differential privacy is used, and fog nodes are used to address the problem of the lower bandwidth and latency in this proposed scheme. The noise is produced by the epsilon-differential mechanism, which is then added to the data. Moreover, the noise is injected at the data owner site to protect the owners data. Fog nodes collect the noise-added data from the data owners, then shift it to the cloud platform for storage, computation, and performing the classification tasks purposes.

cs.CR↗

arXiv2022

NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation

Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on. In this paper, we present NL-Augmenter, a new participatory Python-based natural language augmentation framework which supports the creation of both transformations (modifications to the data) and filters (data splits according to specific features). We describe the framework and an initial set of 117 transformations and 23 filters for a variety of natural language tasks. We demonstrate the efficacy of NL-Augmenter by using several of its transformations to analyze the robustness of popular natural language models. The infrastructure, datacards and robustness analysis results are available publicly on the NL-Augmenter repository (https://github.com/GEM-benchmark/NL-Augmenter).

cs.CL↗

arXiv2022

Quantum Machine Learning for Chemistry and Physics

Machine learning (ML) has emerged into formidable force for identifying hidden but pertinent patterns within a given data set with the objective of subsequent generation of automated predictive behavior. In the recent years, it is safe to conclude that ML and its close cousin deep learning (DL) have ushered unprecedented developments in all areas of physical sciences especially chemistry. Not only the classical variants of ML , even those trainable on near-term quantum hardwares have been developed with promising outcomes. Such algorithms have revolutionzed material design and performance of photo-voltaics, electronic structure calculations of ground and excited states of correlated matter, computation of force-fields and potential energy surfaces informing chemical reaction dynamics, reactivity inspired rational strategies of drug designing and even classification of phases of matter with accurate identification of emergent criticality. In this review we shall explicate a subset of such topics and delineate the contributions made by both classical and quantum computing enhanced machine learning algorithms over the past few years. We shall not only present a brief overview of the well-known techniques but also highlight their learning strategies using statistical physical insight. The objective of the review is to not only to foster exposition to the aforesaid techniques but also to empower and promote cross-pollination among future-research in all areas of chemistry which can benefit from ML and in turn can potentially accelerate the growth of such algorithms.

physics.chem-ph↗

arXiv2022

'John ate 5 apples' != 'John ate some apples': Self-Supervised Paraphrase Quality Detection for Algebraic Word Problems

This paper introduces the novel task of scoring paraphrases for Algebraic Word Problems (AWP) and presents a self-supervised method for doing so. In the current online pedagogical setting, paraphrasing these problems is helpful for academicians to generate multiple syntactically diverse questions for assessments. It also helps induce variation to ensure that the student has understood the problem instead of just memorizing it or using unfair means to solve it. The current state-of-the-art paraphrase generation models often cannot effectively paraphrase word problems, losing a critical piece of information (such as numbers or units) which renders the question unsolvable. There is a need for paraphrase scoring methods in the context of AWP to enable the training of good paraphrasers. Thus, we propose ParaQD, a self-supervised paraphrase quality detection method using novel data augmentations that can learn latent representations to separate a high-quality paraphrase of an algebraic question from a poor one by a wide margin. Through extensive experimentation, we demonstrate that our method outperforms existing state-of-the-art self-supervised methods by up to 32% while also demonstrating impressive zero-shot performance.

cs.CL↗

arXiv2022

Variational Approach to Quantum State Tomography based on Maximal Entropy Formalism

Quantum state tomography is an integral part of quantum computation and offers the starting point for the validation of various quantum devices. One of the central tasks in the field of state tomography is to reconstruct with high fidelity, the quantum states of a quantum system. From an experiment on a real quantum device, one can obtain the mean measurement values of different operators. With such a data as input, in this report we employ the maximal entropy formalism to construct the least biased mixed quantum state that is consistent with the given set of expectation values. Even though in principle, the reported formalism is quite general and should work for an arbitrary set of observables, in practice we shall demonstrate the efficacy of the algorithm on an informationally complete (IC) set of Hermitian operators. Such a set possesses the advantage of uniquely specifying a single quantum state from which the experimental measurements have been sampled and hence renders the rare opportunity to not only construct a least-biased quantum state but even replicate the exact state prepared experimentally within a preset tolerance. The primary workhorse of the algorithm is re-constructing an energy function which we designate as the effective Hamiltonian of the system, and parameterizing it with Lagrange multipliers, according to the formalism of maximal entropy. These parameters are thereafter optimized variationally so that the reconstructed quantum state of the system converges to the true quantum state within an error threshold. To this end, we employ a parameterized quantum circuit and a hybrid quantum-classical variational algorithm to obtain such a target state making our recipe easily implementable on a near-term quantum device.

quant-ph↗

arXiv2022

$Δ$NO and the complexities of electron correlation in simple hydrogen clusters

The $Δ$NO two-electron density matrix (2-RDM) and energy expression are derived from a multideterminantal wave function. The approximate $Δ$NO 2-RDM is combined with an on-top density functional and a double-counting correction to capture electron correlation. A trust-region Newton's method optimization algorithm for the simultaneous optimization of $Δ$NO orbitals and occupancies is introduced and compared to the previous iterative diagonalization algorithm. The combination of $Δ$NO and two different on-top density functionals, Colle-Salvetti (CS) and OF, is assessed on small hydrogen clusters and compared to density functional, single-reference coupled cluster, and multireference perturbation theory (MRMP2) methods. The $Δ$NO-CS and $Δ$NO-OF methods outperform the single-reference methods, and are comparable to MRMP2. However, there is a distinct qualitative error in the $Δ$NO potential energy surface for H$_4$ compared to the exact. This discrepancy is explained through analysis of the $Δ$NO orbitals, occupancies and the two-electron density.

physics.chem-ph↗

arXiv2021

Decomposition and Adaptive Sampling for Data-Driven Inverse Linear Optimization

This work addresses inverse linear optimization where the goal is to infer the unknown cost vector of a linear program. Specifically, we consider the data-driven setting in which the available data are noisy observations of optimal solutions that correspond to different instances of the linear program. We introduce a new formulation of the problem that, compared to other existing methods, allows the recovery of a less restrictive and generally more appropriate admissible set of cost estimates. It can be shown that this inverse optimization problem yields a finite number of solutions, and we develop an exact two-phase algorithm to determine all such solutions. Moreover, we propose an efficient decomposition algorithm to solve large instances of the problem. The algorithm extends naturally to an online learning environment where it can be used to provide quick updates of the cost estimate as new data becomes available over time. For the online setting, we further develop an effective adaptive sampling strategy that guides the selection of the next samples. The efficacy of the proposed methods is demonstrated in computational experiments involving two applications, customer preference learning and cost estimation for production planning. The results show significant reductions in computation and sampling efforts.

math.OC↗

arXiv2021

A Survey and Comparative Study on Multi-Cloud Architectures: Emerging Issues And Challenges For Cloud Federation

Multi-cloud concept has broaden the world of cloud computing and has become a buzzword today. The word Multi-cloud envisions utilization of services from multiple heterogeneous cloud providers via a single architecture at customer premises. Though cloud computing has many issues and offers open research challenges, still the academics and industrial research has paved a pathway for multi-cloud environment. The concept of multi-cloud is in maturing phase, and many research projects are in progress to provide a multi-cloud architecture which is successfully enabled in all the respects like easy configuration, security, management etc. In this paper, concepts, challenges, requirement and future directions for multi-cloud environment are discussed. A survey of existing approaches and solutions provided by different multi-cloud architectures is entailed along with analysis of the pros and cons of different architectures while comparing the same.

cs.DC↗

arXiv2021

Data Security and Privacy in Cloud Computing: Concepts and Emerging Trends

Millions of users across the world leverages data processing and sharing benefits from cloud environment. Data security and privacy are inevitable requirement of cloud environment. Massive usage and sharing of data among users opens door to security loopholes. This paper envisages a discussion of cloud environment, its utilities, challenges, and emerging research trends confined to secure processing and sharing of data.

cs.CR↗

arXiv2021

Convergence of reconstructed density matrix to a pure state using maximal entropy approach

Impressive progress has been made in the past decade in the study of technological applications of varied types of quantum systems. With industry giants like IBM laying down their roadmap for scalable quantum devices with more than 1000-qubits by the end of 2023, efficient validation techniques are also being developed for testing quantum processing on these devices. The characterization of a quantum state is done by experimental measurements through the process called quantum state tomography (QST) which scales exponentially with the size of the system. However, QST performed using incomplete measurements is aptly suited for characterizing these quantum technologies especially with the current nature of noisy intermediate-scale quantum (NISQ) devices where not all mean measurements are available with high fidelity. We, hereby, propose an alternative approach to QST for the complete reconstruction of the density matrix of a quantum system in a pure state for any number of qubits by applying the maximal entropy formalism on the pairwise combinations of the known mean measurements. This approach provides the best estimate of the target state when we know the complete set of observables which is the case of convergence of the reconstructed density matrix to a pure state. Our goal is to provide a practical inference of a quantum system in a pure state that can find its applications in the field of quantum error mitigation on a real quantum computer that we intend to investigate further.

quant-ph↗

arXiv2021

Evaluation of deep learning models for multi-step ahead time series prediction

Time series prediction with neural networks has been the focus of much research in the past few decades. Given the recent deep learning revolution, there has been much attention in using deep learning models for time series prediction, and hence it is important to evaluate their strengths and weaknesses. In this paper, we present an evaluation study that compares the performance of deep learning models for multi-step ahead time series prediction. The deep learning methods comprise simple recurrent neural networks, long short-term memory (LSTM) networks, bidirectional LSTM networks, encoder-decoder LSTM networks, and convolutional neural networks. We provide a further comparison with simple neural networks that use stochastic gradient descent and adaptive moment estimation (Adam) for training. We focus on univariate time series for multi-step-ahead prediction from benchmark time-series datasets and provide a further comparison of the results with related methods from the literature. The results show that the bidirectional and encoder-decoder LSTM network provides the best performance in accuracy for the given time series problems.

cs.LG↗

arXiv2021

Relation Matters in Sampling: A Scalable Multi-Relational Graph Neural Network for Drug-Drug Interaction Prediction

Sampling is an established technique to scale graph neural networks to large graphs. Current approaches however assume the graphs to be homogeneous in terms of relations and ignore relation types, critically important in biomedical graphs. Multi-relational graphs contain various types of relations that usually come with variable frequency and have different importance for the problem at hand. We propose an approach to modeling the importance of relation types for neighborhood sampling in graph neural networks and show that we can learn the right balance: relation-type probabilities that reflect both frequency and importance. Our experiments on drug-drug interaction prediction show that state-of-the-art graph neural networks profit from relation-dependent sampling in terms of both accuracy and efficiency.

cs.LG↗

arXiv2021

SEMIE: SEMantically Infused Embeddings with Enhanced Interpretability for Domain-specific Small Corpus

Word embeddings are a basic building block of modern NLP pipelines. Efforts have been made to learn rich, efficient, and interpretable embeddings for large generic datasets available in the public domain. However, these embeddings have limited applicability for small corpora from specific domains such as automotive, manufacturing, maintenance and support, etc. In this work, we present a comprehensive notion of interpretability for word embeddings and propose a novel method to generate highly interpretable and efficient embeddings for a domain-specific small corpus. We report the evaluation results of our resulting word embeddings and demonstrate their novel features for enhanced interpretability.

cs.CL↗

arXiv2021

Delhi air quality prediction using LSTM deep learning models with a focus on COVID-19 lockdown

Air pollution has a wide range of implications on agriculture, economy, road accidents, and health. In this paper, we use novel deep learning methods for short-term (multi-step-ahead) air-quality prediction in selected parts of Delhi, India. Our deep learning methods comprise of long short-term memory (LSTM) network models which also include some recent versions such as bidirectional-LSTM and encoder-decoder LSTM models. We use a multivariate time series approach that attempts to predict air quality for 10 prediction horizons covering total of 80 hours and provide a long-term (one month ahead) forecast with uncertainties quantified. Our results show that the multivariate bidirectional-LSTM model provides best predictions despite COVID-19 impact on the air-quality during full and partial lockdown periods. The effect of COVID-19 on the air quality has been significant during full lockdown; however, there was unprecedented growth of poor air quality afterwards.

cs.LG↗

arXiv2020

Maximal entropy approach for quantum state tomography

Quantum computation has been growing rapidly in both theory and experiments. In particular, quantum computing devices with a large number of qubits have been developed by IBM, Google, IonQ, and others. The current quantum computing devices are noisy intermediate-scale quantum $($NISQ$)$ devices, and so approaches to validate quantum processing on these quantum devices are needed. One of the most common ways of validation for an n-qubit quantum system is quantum tomography, which tries to reconstruct a quantum system's density matrix by a complete set of observables. However, the inherent noise in the quantum systems and the intrinsic limitations poses a critical challenge to precisely know the actual measurement operators which make quantum tomography impractical in experiments. Here, we propose an alternative approach to quantum tomography, based on the maximal information entropy, that can predict the values of unknown observables based on the available mean measurement data. This can then be used to reconstruct the density matrix with high fidelity even though the results for some observables are missing. Of additional contexts, a practical approach to the inference of the quantum mechanical state using only partial information is also needed.

quant-ph↗

arXiv2020

Towards Semantic Noise Cleansing of Categorical Data based on Semantic Infusion

Semantic Noise affects text analytics activities for the domain-specific industries significantly. It impedes the text understanding which holds prime importance in the critical decision making tasks. In this work, we formalize semantic noise as a sequence of terms that do not contribute to the narrative of the text. We look beyond the notion of standard statistically-based stop words and consider the semantics of terms to exclude the semantic noise. We present a novel Semantic Infusion technique to associate meta-data with the categorical corpus text and demonstrate its near-lossless nature. Based on this technique, we propose an unsupervised text-preprocessing framework to filter the semantic noise using the context of the terms. Later we present the evaluation results of the proposed framework using a web forum dataset from the automobile-domain.

cs.CL↗

arXiv2019

DiffQue: Estimating Relative Difficulty of Questions in Community Question Answering Services

Automatic estimation of relative difficulty of a pair of questions is an important and challenging problem in community question answering (CQA) services. There are limited studies which addressed this problem. Past studies mostly leveraged expertise of users answering the questions and barely considered other properties of CQA services such as metadata of users and posts, temporal information and textual content. In this paper, we propose DiffQue, a novel system that maps this problem to a network-aided edge directionality prediction problem. DiffQue starts by constructing a novel network structure that captures different notions of difficulties among a pair of questions. It then measures the relative difficulty of two questions by predicting the direction of a (virtual) edge connecting these two questions in the network. It leverages features extracted from the network structure, metadata of users/posts and textual description of questions and answers. Experiments on datasets obtained from two CQA sites (further divided into four datasets) with human annotated ground-truth show that DiffQue outperforms four state-of-the-art methods by a significant margin (28.77% higher F1 score and 28.72% higher AUC than the best baseline). As opposed to the other baselines, (i) DiffQue appropriately responds to the training noise, (ii) DiffQue is capable of adapting multiple domains (CQA datasets), and (iii) DiffQue can efficiently handle 'cold start' problem which may arise due to the lack of information for newly posted questions or newly arrived users.

cs.LG↗