Vikram Singh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Vikram Singh has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Lov Kumar
National Institute of Technology Kurukshetra, Kurukshetra, India
7 shared publications - Aneesh Krishna
Curtin University
4 shared publications - Kuldeep Singh
National Institute of Technology
2 shared publications Pawan Kumar
National Institute of Technology
2 shared publicationsReiben Eappen Reji
National Institute of Technology
2 shared publications- Amit
National Institute of Technology
1 shared publication
Latest Publications
- 3 June 2026
- Published by Springer Nature
- p. 125-137
Mitigating Data Sparsity in Recommender Systems Using Hybrid Cross-Domain Learning Strategy
- 3 June 2026
- Published by Springer Nature
- p. 125-137
Mitigating Data Sparsity in Recommender Systems Using Hybrid Cross-Domain Learning Strategy
- 21 April 2026
- Published by Springer Nature
- p. 217-225
Feature Selection and SHAP-Based Interpretability in ML Models for AMR Prediction in Klebsiella Pneumoniae
- 21 April 2026
- Published by Springer Nature
- p. 217-225
Feature Selection and SHAP-Based Interpretability in ML Models for AMR Prediction in Klebsiella Pneumoniae
- Open Access
- 1 April 2025
- Published by Wiley
Cross-domain Learning Framework for Book-Movie Recommendation with RoBERTa and DistilBERT in Action
Recommender systems (RSs) aim to streamline navigation through vast product repositories, with personalization as a critical development. However, modeling user preferences remains challenging due to their dynamic and complexity. Cross-domain learning (CDL) has emerged as a promising approach to enhance personalization by leveraging inter-domain knowledge. Despite advancements, modeling inter-domain knowledge is difficult due to the semantic heterogeneity of participating domains. This paper presents a cross-domain recommendation (CDR) framework and evaluates its effectiveness on ’Book-Movie’ item pairs, leveraging books as auxiliary data to enhance movie recommendations. Books offer richer contextual insights into users’ cognitive states, thereby addressing legacy challenges such as data sparsity and the cold-start problem. Using pre-trained models such as RoBERTa and DistilBERT, we propose a novel approach for inter-domain knowledge modeling, leveraging the capability of generative models to effectively capture inter-domain knowledge and transfer it to achieve a higher level of personalization in the target domain. RoBERTa, fine-tuned on book data, effectively captures contextual relationships and bridging semantic gaps between domains, whereas DistilBERT captures deep semantic relationships between the textual content of the book and movie domains. Evaluation metrics include LRAP, cross-entropy loss, and precision. RoBERTa outperformed DistilBERT, achieving LRAP (0.908), cross-entropy (0.269), and precision (0.96). Similarity measures, including domain overlap (0.992), domain generalization (0.7895), pairwise difference on Genre (1.418), and Exact Match Ratio (0.60) highlight strong alignment between book and movie genres. This work emphasizes a multi-label classification strategy and novel algorithm for cross-domain knowledge modeling, offering a robust solution for CDR challenges with effective trade-off metrics.
- 1 April 2025
- Published by Wiley
Open AccessCross-domain Learning Framework for Book-Movie Recommendation with RoBERTa and DistilBERT in Action
Recommender systems (RSs) aim to streamline navigation through vast product repositories, with personalization as a critical development. However, modeling user preferences remains challenging due to their dynamic and complexity. Cross-domain learning (CDL) has emerged as a promising approach to enhance personalization by leveraging inter-domain knowledge. Despite advancements, modeling inter-domain knowledge is difficult due to the semantic heterogeneity of participating domains. This paper presents a cross-domain recommendation (CDR) framework and evaluates its effectiveness on ’Book-Movie’ item pairs, leveraging books as auxiliary data to enhance movie recommendations. Books offer richer contextual insights into users’ cognitive states, thereby addressing legacy challenges such as data sparsity and the cold-start problem. Using pre-trained models such as RoBERTa and DistilBERT, we propose a novel approach for inter-domain knowledge modeling, leveraging the capability of generative models to effectively capture inter-domain knowledge and transfer it to achieve a higher level of personalization in the target domain. RoBERTa, fine-tuned on book data, effectively captures contextual relationships and bridging semantic gaps between domains, whereas DistilBERT captures deep semantic relationships between the textual content of the book and movie domains. Evaluation metrics include LRAP, cross-entropy loss, and precision. RoBERTa outperformed DistilBERT, achieving LRAP (0.908), cross-entropy (0.269), and precision (0.96). Similarity measures, including domain overlap (0.992), domain generalization (0.7895), pairwise difference on Genre (1.418), and Exact Match Ratio (0.60) highlight strong alignment between book and movie genres. This work emphasizes a multi-label classification strategy and novel algorithm for cross-domain knowledge modeling, offering a robust solution for CDR challenges with effective trade-off metrics.
- Open Access
- 22 March 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 174
Nested deep learning with learned network embeddings for software defect prediction
- 22 March 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 174
Open AccessNested deep learning with learned network embeddings for software defect prediction
- 6 December 2024
- Published by Springer Nature
- p. 309-319
Temporal Intelligence: Recognizing User Activities with Stacked LSTM Networks
- 6 December 2024
- Published by Springer Nature
- p. 309-319
Temporal Intelligence: Recognizing User Activities with Stacked LSTM Networks
- 30 November 2024
- Published by Springer Nature
- p. 91-100
Connecting Words to Motion: Unleashing Video Highlights and Moments Through Cross Attention Temporal Grounding
- 30 November 2024
- Published by Springer Nature
- p. 91-100
Connecting Words to Motion: Unleashing Video Highlights and Moments Through Cross Attention Temporal Grounding
- 24 July 2024
- Published by Springer Nature
- p. 586-596
Modeling Topic Evolution to Steer Interactive Information Search
- 24 July 2024
- Published by Springer Nature
- p. 586-596
Modeling Topic Evolution to Steer Interactive Information Search
- 10 April 2024
- Published by Springer Nature
- p. 234-244
An Empirical Analysis on Leveraging User Reviews with NLP-Enhanced Word Embeddings for App Rating Prediction
- 10 April 2024
- Published by Springer Nature
- p. 234-244
An Empirical Analysis on Leveraging User Reviews with NLP-Enhanced Word Embeddings for App Rating Prediction
- 10 April 2024
- Published by Springer Nature
- p. 292-302
Investigating BERT Layer Performance and SMOTE Through MLP-Driven Ablation on Gittercom
- 10 April 2024
- Published by Springer Nature
- p. 292-302
Investigating BERT Layer Performance and SMOTE Through MLP-Driven Ablation on Gittercom