Vishal Srivastava

Vishal Srivastava

Auto-generated profile, based on publicly available information

Vishal Srivastava

Department of Computer Science and Engineering, Motilal Nehru National Institute of Technology

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 November 2024 in ACM Computing Surveys
Verified
Journal Article
Open access
HPHaseena Rahmath P
Haseena Rahmath P
VSVishal Srivastava
Vishal Srivastava
KCKuldeep Chaurasia
Kuldeep Chaurasia
RPRoberto Gonçalves Pacheco
Roberto Gonçalves Pacheco
RCRodrigo Couto
Rodrigo Couto
Deep neural networks (DNNs) typically have a single exit point that makes predictions by running the entire stack of neural layers. Since not all inputs require the same amount of computation to reach a confident prediction, recent research has focused on incorporating multiple “exits” into the conventional DNN architecture. Early-exit DNNs are multi-exit neural networks that attach many side branches to the conventional DNN, enabling inference to stop early at intermediate points. This approach offers several advantages, including speeding up the inference process, mitigating the vanishing gradients problems, reducing overfitting and overthinking tendencies. It also supports DNN partitioning across devices and is ideal for multi-tier computation platforms such as edge computing. This article decomposes the early-exit DNN architecture and reviews the recent advances in the field. The study explores its benefits, designs, training strategies, and adaptive inference mechanisms. Various design challenges, application scenarios, and future directions are also extensively discussed.

9 May 2023 in ACM Transactions on Asian and Low-Resource Language Information Processing
Verified
Journal Article
Open access
Shashank SinghShashank Singh
Shashank Singh
VSVishal Srivastava
Vishal Srivastava
AKAjay Kumar
Ajay Kumar
STShailendra Tiwari
Shailendra Tiwari
Dilbag SinghDilbag Singh
Dilbag Singh
Heung No LeeHeung No Lee
Heung No Lee
The rapid growth in popularity of online social networks provides new opportunities in computer science, sociology, math, information studies, biology, business, and more. Social network analysis (SNA) is a paramount technique supporting understanding social relationships and networks. Accordingly, certain studies and reviews have been presented focusing on information dissemination, influence analysis, link prediction, and more. However, the ultimate aim is for social network background knowledge and analysis to solve real-world social network problems. SNA still has several research challenges in this context, including users’ privacy in online social networks. Inspired by these facts, we have presented a survey on social network analysis techniques, visualization, structure, privacy, and applications. This detailed study has started with the basics of network representation, structure, and measures. Our primary focus is on SNA applications with state-of-the-art techniques. We further provide a comparative analysis of recent developments on SNA problems in the sequel. The privacy preservation with SNA is also surveyed. In the end, research challenges and future directions are discussed to suggest to researchers a starting point for their research.

3 June 2025 in IEEE Access
Verified
Journal Article
Open access
Shashank SinghShashank Singh
Shashank Singh
KSKuldeep Singh
Kuldeep Singh
VSVishal Srivastava
Vishal Srivastava
HSHarish Kumar Shakya
Harish Kumar Shakya
As the big data era transforms the information analysis landscape, social network (SN) analytics has emerged as a critical discipline to understand complex relationships and interactions within enormous social systems. This study aims to provide a comprehensive overview of SN analytics as big data, providing an in-depth exploration of concepts, methods, and applications within this rapidly evolving field. The survey covers a wide range of topics, including methods for pre-processing and cleaning social network data, as well as more advanced analytical approaches such as opinion mining, sentiment analysis, text mining, and natural language processing. It also discusses various big data architectures for SN analytics, like Lambda architecture, Kappa architecture, and GraphX architecture. In addition, it covers issues of scalability, data quality, privacy, and real-time analysis. SN analytics can be useful for researchers from across domains like business and marketing, healthcare and biomedicine, social sciences and psychology, politics and governance, cybersecurity and fraud detection, recommendation systems, crisis management, and disaster response to extract crucial information from vast datasets and formulate domain-specific strategies.

8 November 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
Shashank SinghShashank Singh
Shashank Singh
VSVishal Srivastava
Vishal Srivastava
AKAvadh Kishor
Avadh Kishor
JBJayendra Barua
Jayendra Barua
Neeraj KumarNeeraj Kumar
Neeraj Kumar
Influence maximization (IM) problem widely motivated researchers due to its application potential in computer science and social sciences. Most recent advances focus on positive relations (friends, trust, etc.) in unsigned social networks. IM is not explored well in signed networks by adopting positive and negative associations (foe, distrust, etc.). Therefore, this study surveys the IM problem in signed social networks. This is the first survey to explore the polarity-related IM problem in networks to the best of our knowledge. First, we discussed the social network’s fundamentals and polarity to build the foundation for the IM problem. Then, we described the information propagation process and models for signed social networks. After, we will present a discussion and comparison of the polarity-based IM state-of-the-art algorithms with performance evaluations. At last, we have explored the research challenges of signed networks and discussed future directions. Finally, we also discuss some open problems.

4 July 2024 in IEEE Transactions on Network Science and Engineering
Verified
Journal Article
Closed access
VSVishal Srivastava
Vishal Srivastava
Shashank SinghShashank Singh
Shashank Singh
AJAnkush Jain
Ankush Jain
Network partitioning has been studied extensively on undirected and weighted networks that need to partition the graph into small clusters. Graph-cutting is a widely known approach that removes the inter-cluster edges to find the local network clusters. Cutting a network into small clusters is pivotal in a mixed integer optimization problem. Proper selection of cut sequences discards the possibility of trivial partitions and reduces the computation load to improve cluster quality. Proper cut-sequence selection relies on multiple heuristics that restrict this problem from being generalized. Cut-sequence selection is an NP-hard problem that turns out to be challenging for weighted networks. This paper presents a swarm-heuristics-based framework to solve the cut-sequence selection problem in weighted networks. First, we generate an affinity network from a given data set. A cost-based objective function is formalized that takes cut sequences as input and returns the weighted intra-cluster connected components. Subsequently, heuristics-based cut sequences are initialized, and krill-herd optimization is used to solve the objective function. The framework is empirically tested on simulated and real-world networks. Network-based indices are used to measure the quality of partitions. The comparative analysis, computation time, and convergence analysis are performed with state-of-the-art methods to report the competitive behavior of the framework. The framework is highly effective and has paved new ways for future research to solve the cut-sequence selection problem without prior knowledge.

25 March 2023
Verified
Book Chapter
Closed access
PDF file
PRP. Haseena Rahmath
P. Haseena Rahmath
VSVishal Srivastava
Vishal Srivastava
KCKuldeep Chaurasia
Kuldeep Chaurasia