Prajjwal Nijhara

2026

1. SIGMOD

   PJsim: Towards Precise and Scalable Graph Similarity

   Prajjwal Nijhara, Jainan Tandel, Rohit Prajapati, and 1 more author

   Proceedings of the ACM on Management of Data, 2026

   Bib

   @article{Nijhara2026PJsim,
     title = {PJsim: Towards Precise and Scalable Graph Similarity},
     author = {Nijhara, Prajjwal and Tandel, Jainan and Prajapati, Rohit and Banerjee, Dip Sankar},
     journal = {Proceedings of the ACM on Management of Data},
     volume = {4},
     year = {2026},
     publisher = {ACM New York, NY, USA},
   }

2. GPGPU@ASPLOS

   TC-MIS: Maximal Independent Sets on Tensor Cores

   Prajjwal Nijhara, and Dip Sankar Banerjee

   In Proceedings of the 18th Workshop on General Purpose Processing Unit Using GPU held in conjunction with ACM International Conference on Architectural Support for Programming Languages and Operating Systems (GPGPU@ASPLOS), 2026

   Bib

   @inproceedings{Nijhara2026TCMIS,
     author = {Nijhara, Prajjwal and Banerjee, Dip Sankar},
     title = {TC-MIS: Maximal Independent Sets on Tensor Cores},
     booktitle = {Proceedings of the 18th Workshop on General Purpose Processing Unit Using GPU held in conjunction with ACM International Conference on Architectural Support for Programming Languages and Operating Systems (GPGPU@ASPLOS)},
     year = {2026},
     address = {Pittsburgh, USA}
   }

3. ICDCN

   A Precise and Closed-Form Solution for Edge-Ranking

   Prajjwal Nijhara, Jainan Tandel, Rohit Prajapati, and 1 more author

   In Proceedings of the 27th International Conference on Distributed Computing and Networking (ICDCN), 2026

   Bib

   @inproceedings{Nijhara2026Precise,
     author = {Nijhara, Prajjwal and Tandel, Jainan and Prajapati, Rohit and Banerjee, Dip Sankar},
     title = {A Precise and Closed-Form Solution for Edge-Ranking},
     booktitle = {Proceedings of the 27th International Conference on Distributed Computing and Networking (ICDCN)},
     year = {2026},
     address = {Nara, Japan}
   }

2025

1. ICPP

   Efficient Parallel Algorithms for Dynamic Percolation Centrality

   Prajjwal Nijhara, Lokesh Venkatachalam, Agam Harpreet Singh, and 4 more authors

   In Proceedings of the 54th International Conference on Parallel Processing (ICPP), 2025

   Bib

   @inproceedings{Nijhara2025DynamicPercolationCentrality,
     author = {Nijhara, Prajjwal and Venkatachalam, Lokesh and Singh, Agam Harpreet and Chandramouli, Athreya and Jana, Sayantan and Kothapalli, Kishore and Banerjee, Dip Sankar},
     title = {Efficient Parallel Algorithms for Dynamic Percolation Centrality},
     booktitle = {Proceedings of the 54th International Conference on Parallel Processing (ICPP)},
     year = {2025},
     address = {San Diego, USA}
   }

2. PDP

   Fast Maximal Independent Sets on Dynamic Graphs

   Prajjwal Nijhara, Aditya Trivedi, and Dip Sankar Banerjee

   In 33rd Euromicro/IEEE International Conference on Parallel, Distributed, and Network-Based Processing (PDP 2025) , Mar 2025

   Bib

   @inproceedings{nijhara2025mis,
     author = {Nijhara, Prajjwal and Trivedi, Aditya and Banerjee, Dip Sankar},
     booktitle = { 33rd Euromicro/IEEE International Conference on Parallel, Distributed, and Network-Based Processing (PDP 2025) },
     title = {{ Fast Maximal Independent Sets on Dynamic Graphs }},
     year = {2025},
     volume = {},
     issn = {},
     month = mar
   }

3. PDP

   Fast Katz Centrality on Dynamic Graphs

   Prajjwal Nijhara, Dishit Sharma, and Dip Sankar Banerjee

   In 33rd Euromicro/IEEE International Conference on Parallel, Distributed, and Network-Based Processing (PDP 2025) , Mar 2025

   Bib

   @inproceedings{nijhara2025katz,
     author = {Nijhara, Prajjwal and Sharma, Dishit and Banerjee, Dip Sankar},
     booktitle = { 33rd Euromicro/IEEE International Conference on Parallel, Distributed, and Network-Based Processing (PDP 2025) },
     title = {{ Fast Katz Centrality on Dynamic Graphs }},
     year = {2025},
     volume = {},
     issn = {},
     month = mar
   }

2024

1. HiPCW

   Fast MIS on Incremental Graphs

   Aditya Trivedi, Prajjwal Nijhara, and Dip Sankar Banerjee

   In 2024 IEEE 31st International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW) , Dec 2024

   Abs Bib

   Maintaining the Maximal Independent Set (MIS) in dynamic graphs is crucial for applications like resource allocation, load balancing, and network optimization. Traditional approaches require complete re-computation, making them inefficient for large and evolving graphs. Our proposed methods utilize Tuple Valued Bitmap (TVB) and its extension with levels, TVBL, to enhance parallelism and minimize search space. Experimental evaluations on large-scale graphs, ranging from 50 million to 1.2 billion edges, demonstrate significant speedups—up to 15.64x for insertions, with minimal impact on the MIS cardinality. This approach offers a scalable solution for dynamic graphs, paving the way for further optimization in fully dynamic and streaming settings.

   @inproceedings{10898364,
     author = {Trivedi, Aditya and Nijhara, Prajjwal and Banerjee, Dip Sankar},
     booktitle = { 2024 IEEE 31st International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW) },
     title = {{ Fast MIS on Incremental Graphs }},
     year = {2024},
     volume = {},
     issn = {},
     pages = {139-140},
     keywords = {High performance computing;Conferences;Parallel processing;Load management;Dynamic scheduling;Distance measurement;Resource management;Optimization},
     doi = {10.1109/HiPCW63042.2024.00047},
     url = {https://doi.ieeecomputersociety.org/10.1109/HiPCW63042.2024.00047},
     publisher = {IEEE Computer Society},
     address = {Los Alamitos, CA, USA},
     month = dec
   }

2. HiPCW

   Parallel Katz Centrality On Evolving Graphs

   Dishit Sharma, Prajjwal Nijhara, and Dip Sankar Banerjee

   In 2024 IEEE 31st International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW) , Dec 2024

   Abs Bib

   Katz centrality measures a node’s influence within a network, considering the total number of walks between pairs of nodes rather than solely the shortest paths. This paper presents an algorithm for dynamically updating Katz centrality scores as the underlying graph evolves. Our method employs a frontier-based breadth-first search (BFS) to efficiently derive updated Katz scores in dynamic graphs. Notably, our algorithm accommodates node insertions and deletions, addressing a significant limitation of current state-of-the-art methods.

   @inproceedings{10898741,
     author = {Sharma, Dishit and Nijhara, Prajjwal and Banerjee, Dip Sankar},
     booktitle = { 2024 IEEE 31st International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW) },
     title = {{ Parallel Katz Centrality On Evolving Graphs }},
     year = {2024},
     volume = {},
     issn = {},
     pages = {193-194},
     keywords = {Heuristic algorithms;High performance computing;Conferences},
     doi = {10.1109/HiPCW63042.2024.00074},
     url = {https://doi.ieeecomputersociety.org/10.1109/HiPCW63042.2024.00074},
     publisher = {IEEE Computer Society},
     address = {Los Alamitos, CA, USA},
     month = dec
   }

3. HiPCW

   Efficient Parallel Algorithms For Exact SimRank Computations

   Aditya Mundhara, Prajjwal Nijhara, and Dip Sankar Banerjee

   In 2024 IEEE 31st International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW) , Dec 2024

   Abs Bib

   SimRank is a popular measure for evaluating node similarities in graphs, but its high computational cost limits scalability for large graphs. The ExactSim [1] algorithm achieves precise single-source SimRank similarities but suffers from significant computation time. In this work, we parallelize key components of ExactSim — Personalized PageRank (PPR) computations and SimRank calculations on a CPU-based shared memory multi-core system. By optimizing these modules, we significantly reduce runtime, making ExactSim more practical for large-scale applications. Our results (on graph sizes ranging from 0.1 million edges to 100 million edges) demonstrate the effectiveness of parallelization in improving both efficiency and scalability.

   @inproceedings{10898914,
     author = {Mundhara, Aditya and Nijhara, Prajjwal and Banerjee, Dip Sankar},
     booktitle = { 2024 IEEE 31st International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW) },
     title = {{ Efficient Parallel Algorithms For Exact SimRank Computations }},
     year = {2024},
     volume = {},
     issn = {},
     pages = {125-126},
     keywords = {Runtime;Scalability;High performance computing;Conferences;Distance measurement;Computational efficiency;Parallel algorithms},
     doi = {10.1109/HiPCW63042.2024.00040},
     url = {https://doi.ieeecomputersociety.org/10.1109/HiPCW63042.2024.00040},
     publisher = {IEEE Computer Society},
     address = {Los Alamitos, CA, USA},
     month = dec
   }

4. HiPCW

   SimRank on Data Streams

   Dhyan Yajnik, Huzefa Aiyub Ansari, Prajjwal Nijhara, and 1 more author

   In 2024 IEEE 31st International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW) , Dec 2024

   Abs Bib

   This paper introduces a novel approach that integrates machine learning techniques to optimize SimRank convergence on streaming data. Our approach utilizes the structural properties of the graph, such as edge features, to train a linear regression model that predicts SimRank values for newly added nodes. These predictions serve as effective initializations, ensuring faster convergence of the SimRank algorithm. By avoiding full recomputation and providing a new direction for research, our method offers a promising solution for similarity computation in evolving networks.

   @inproceedings{10898270,
     author = {Yajnik, Dhyan and Ansari, Huzefa Aiyub and Nijhara, Prajjwal and Banerjee, Dip Sankar},
     booktitle = { 2024 IEEE 31st International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW) },
     title = {{ SimRank on Data Streams }},
     year = {2024},
     volume = {},
     issn = {},
     pages = {137-138},
     keywords = {Machine learning algorithms;High performance computing;Conferences;Computational modeling;Linear regression;Machine learning;Predictive models;Prediction algorithms;Streams;Convergence},
     doi = {10.1109/HiPCW63042.2024.00046},
     url = {https://doi.ieeecomputersociety.org/10.1109/HiPCW63042.2024.00046},
     publisher = {IEEE Computer Society},
     address = {Los Alamitos, CA, USA},
     month = dec
   }