Satya Krishna Nunna
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Satya Krishna Nunna has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Hemantha Kumar Kalluri
Department of Computer Science and Engineering, School of Engineering and Sciences, SRM University AP, Amaravati, Andhra Pradesh, India
4 shared publications D. V. L. N. Somayajulu
IIITDM Kurnool, Jagannathagattu Hill
2 shared publications- Lavanya Parchuri
Queensland University
2 shared publications - Lovely Yeswanth Panchumarthi
Emory University
2 shared publications - Mahesh Kumar Morampudi
SRM University-AP
2 shared publications - Nagesh Bhattu Sristy
Department of Computer Science and Engineering, National Institute of Technology Andhra Pradesh, Tadepalligudem, India
2 shared publications
Latest Publications
- 14 August 2026
- Published by Springer Nature in SN Computer Science
- Vol. 7 (6) , 696
Air Quality Monitoring in Sparse Urban Networks: An Enhanced Fog Hierarchical Federated Learning Approach
- 14 August 2026
- Published by Springer Nature in SN Computer Science
- Vol. 7 (6) , 696
Air Quality Monitoring in Sparse Urban Networks: An Enhanced Fog Hierarchical Federated Learning Approach
- Open Access
- 6 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 53387-53405
DMAHGT: A Dynamic Meta-Attention Heterogeneous Graph Transformer for Robust Node Representation Learning
Heterogeneous Graph Neural Networks have emerged as powerful tools for analyzing complex, multi-typed graph-structured data. However, their performance often varies across domains due to challenges such as handling diverse node and relation types, capturing dynamic temporal patterns, and providing model explainability. To address these limitations, this paper proposes the Dynamic Meta-Attention Heterogeneous Graph Transformer (DMAHGT) as a novel heterogeneous graph model that incorporates four key innovations: a two-level hierarchical attention mechanism for nuanced message passing; dynamic meta-attention that adapts weights based on node features, relation types, and temporal information; meta-learning capabilities for cross-dataset adaptation via a CrossDatasetMetaLearner; and inherent explainability through importance scoring of nodes and features. The proposed model demonstrates robustness and scalability, particularly for real-world applications involving complex and evolving graph structures, such as academic and social networks. Its ability to dynamically adapt to different relational semantics and temporal contexts highlights its potential as a versatile solution for heterogeneous graph-based learning tasks. The proposed model is evaluated on three benchmark datasets—ACM, IMDB, and DBLP—and is comprehensively compared with several state-of-the-art heterogeneous graph models, including HAN, HGT, HGCN, HeteroGNN, IGNN, and the meta-learning baseline MAML. The experimental results demonstrate that DMAHGT consistently outperforms these baseline approaches, achieving superior performance in node classification, clustering, and similarity search tasks.
- 6 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 53387-53405
Open AccessDMAHGT: A Dynamic Meta-Attention Heterogeneous Graph Transformer for Robust Node Representation Learning
Heterogeneous Graph Neural Networks have emerged as powerful tools for analyzing complex, multi-typed graph-structured data. However, their performance often varies across domains due to challenges such as handling diverse node and relation types, capturing dynamic temporal patterns, and providing model explainability. To address these limitations, this paper proposes the Dynamic Meta-Attention Heterogeneous Graph Transformer (DMAHGT) as a novel heterogeneous graph model that incorporates four key innovations: a two-level hierarchical attention mechanism for nuanced message passing; dynamic meta-attention that adapts weights based on node features, relation types, and temporal information; meta-learning capabilities for cross-dataset adaptation via a CrossDatasetMetaLearner; and inherent explainability through importance scoring of nodes and features. The proposed model demonstrates robustness and scalability, particularly for real-world applications involving complex and evolving graph structures, such as academic and social networks. Its ability to dynamically adapt to different relational semantics and temporal contexts highlights its potential as a versatile solution for heterogeneous graph-based learning tasks. The proposed model is evaluated on three benchmark datasets—ACM, IMDB, and DBLP—and is comprehensively compared with several state-of-the-art heterogeneous graph models, including HAN, HGT, HGCN, HeteroGNN, IGNN, and the meta-learning baseline MAML. The experimental results demonstrate that DMAHGT consistently outperforms these baseline approaches, achieving superior performance in node classification, clustering, and similarity search tasks.
- 3 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Comparative Analysis of LLMs in Indic Languages
- 3 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Comparative Analysis of LLMs in Indic Languages
- Open Access
- 5 March 2026
- Published by Springer Nature in Discover Computing
- Vol. 29 (1) , 132
Locality preserving and homomorphically encrypted deep features for privacy-preserving face recognition
- 5 March 2026
- Published by Springer Nature in Discover Computing
- Vol. 29 (1) , 132
Open AccessLocality preserving and homomorphically encrypted deep features for privacy-preserving face recognition
- Open Access
- 20 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 29610-29627
GDNConv: A Novel Graph Deformation Network for Robust Representation Learning on Noisy Graph Structures
Graph Neural Networks have emerged as powerful tools for analyzing graph-structured data. However, their performance often varies across datasets due to challenges such as noisy edges, sparse connectivity, and over-smoothing in deep layers. To address these limitations, Graph Deformation Network Convolution (GDNConv) is proposed as a novel graph convolution model that incorporates four key innovations: dynamic edge weight learning to filter noisy connections, graph attention deformation to prioritize relevant neighbors, multi-level aggregation to capture multi-scale patterns, and self-regularization to stabilize training. This proposed model demonstrates robustness and scalability, particularly for real-world applications involving complex and noisy graph structures, such as social networks and recommendation systems. It has ability to dynamically adapt graph topology during training and superior performance on both dense and sparse datasets highlight its potential as a versatile solution for graph-based learning tasks. Additionally, GDNConv’s computational efficiency and self-regularization mechanisms make it suitable for large-scale applications where resource constraints are a concern. The proposed model is evaluated on four benchmark datasets—Cora, CiteSeer, PubMed, and ogbn-arxiv—and compared with several state-of-the-art models, including Graph Convolutional Network, Graph Attention Network, and Graph Sample and Aggregate. The experimental results demonstrate that the proposed model consistently outperforms these baseline approaches, achieving improvements of 4.7% and 4.2% in both accuracy and F1 score.
- 20 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 29610-29627
Open AccessGDNConv: A Novel Graph Deformation Network for Robust Representation Learning on Noisy Graph Structures
Graph Neural Networks have emerged as powerful tools for analyzing graph-structured data. However, their performance often varies across datasets due to challenges such as noisy edges, sparse connectivity, and over-smoothing in deep layers. To address these limitations, Graph Deformation Network Convolution (GDNConv) is proposed as a novel graph convolution model that incorporates four key innovations: dynamic edge weight learning to filter noisy connections, graph attention deformation to prioritize relevant neighbors, multi-level aggregation to capture multi-scale patterns, and self-regularization to stabilize training. This proposed model demonstrates robustness and scalability, particularly for real-world applications involving complex and noisy graph structures, such as social networks and recommendation systems. It has ability to dynamically adapt graph topology during training and superior performance on both dense and sparse datasets highlight its potential as a versatile solution for graph-based learning tasks. Additionally, GDNConv’s computational efficiency and self-regularization mechanisms make it suitable for large-scale applications where resource constraints are a concern. The proposed model is evaluated on four benchmark datasets—Cora, CiteSeer, PubMed, and ogbn-arxiv—and compared with several state-of-the-art models, including Graph Convolutional Network, Graph Attention Network, and Graph Sample and Aggregate. The experimental results demonstrate that the proposed model consistently outperforms these baseline approaches, achieving improvements of 4.7% and 4.2% in both accuracy and F1 score.
- 2 January 2026
- Published by Springer Nature
- p. 41-53
Modified Cross Encoder for Two-Stage Passage Ranking
- 2 January 2026
- Published by Springer Nature
- p. 41-53
Modified Cross Encoder for Two-Stage Passage Ranking
- 2 January 2026
- Published by Springer Nature
- p. 27-39
Improving Information Retrieval Task with Asymmetric Divergence from Randomness in Query Expansion
- 2 January 2026
- Published by Springer Nature
- p. 27-39
Improving Information Retrieval Task with Asymmetric Divergence from Randomness in Query Expansion
- 15 September 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (14) , 1-23
Performance evaluation of diverse graph-based models on homogeneous datasets
- 15 September 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (14) , 1-23
Performance evaluation of diverse graph-based models on homogeneous datasets
- 15 June 2023
- Published by Springer Nature
- p. 417-429
Face Recognition at Various Angles