Amit Singh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Amit Singh has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Gururaj K
Microsoft, Bengaluru, India
3 shared publications - Jian Jiao
Microsoft, Bellevue, WA, USA
3 shared publications - Manik Varma
Microsoft Research, Bengaluru, Karnataka, India
3 shared publications - Akash Kumar Mohankumar
Microsoft, Bengaluru, Karnataka, India
2 shared publications - Anshul Mittal
Microsoft, Noida, India
2 shared publications - Deepak Saini
Microsoft, Redmond, WA, USA
2 shared publications
Latest Publications
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1409-1420
Scaling the Vocabulary of Non-autoregressive Models for Fast Generative Retrieval
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1409-1420
Open AccessScaling the Vocabulary of Non-autoregressive Models for Fast Generative Retrieval
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 394-402
Graph Regularized Encoder Training for Extreme Classification
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 394-402
Open AccessGraph Regularized Encoder Training for Extreme Classification
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 4124-4133
UniDEC : Unified Dual Encoder and Classifier Training for Extreme Multi-Label Classification
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 4124-4133
Open AccessUniDEC : Unified Dual Encoder and Classifier Training for Extreme Multi-Label Classification
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4745-4751
Unified Generative & Dense Retrieval for Query Rewriting in Sponsored Search
Sponsored search is a key revenue source for search engines, where advertisers bid on keywords to target users or search queries of interest. However, finding relevant keywords for a given query is challenging due to the large and dynamic keyword space, ambiguous user/advertiser intents, and diverse possible topics and languages. In this work, we present a comprehensive comparison between two paradigms for online query rewriting: Generative (NLG) and Dense Retrieval (DR) methods. We observe that both methods offer complementary benefits that are additive. As a result, we show that around 40% of the high-quality keywords retrieved by the two approaches are unique and not retrieved by the other. To leverage the strengths of both methods, we propose CLOVER-Unity, a novel approach that unifies generative and dense retrieval methods in one single model. Through offline experiments, we show that the NLG and DR components of CLOVER-Unity consistently outperform individually trained NLG and DR models on public and internal benchmarks. Furthermore, we show that CLOVER-Unity achieves 9.8% higher good keyword density than the ensemble of two separate DR and NLG models while reducing computational costs by almost half. We conduct extensive online A/B experiments on Microsoft Bing in 140+ countries and achieve improved user engagement, with an average increase in total clicks by 0.89% and increased revenue by 1.27%. We also share our practical lessons and optimization tricks for deploying such unified models in production.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4745-4751
Open AccessUnified Generative & Dense Retrieval for Query Rewriting in Sponsored Search
Sponsored search is a key revenue source for search engines, where advertisers bid on keywords to target users or search queries of interest. However, finding relevant keywords for a given query is challenging due to the large and dynamic keyword space, ambiguous user/advertiser intents, and diverse possible topics and languages. In this work, we present a comprehensive comparison between two paradigms for online query rewriting: Generative (NLG) and Dense Retrieval (DR) methods. We observe that both methods offer complementary benefits that are additive. As a result, we show that around 40% of the high-quality keywords retrieved by the two approaches are unique and not retrieved by the other. To leverage the strengths of both methods, we propose CLOVER-Unity, a novel approach that unifies generative and dense retrieval methods in one single model. Through offline experiments, we show that the NLG and DR components of CLOVER-Unity consistently outperform individually trained NLG and DR models on public and internal benchmarks. Furthermore, we show that CLOVER-Unity achieves 9.8% higher good keyword density than the ensemble of two separate DR and NLG models while reducing computational costs by almost half. We conduct extensive online A/B experiments on Microsoft Bing in 140+ countries and achieve improved user engagement, with an average increase in total clicks by 0.89% and increased revenue by 1.27%. We also share our practical lessons and optimization tricks for deploying such unified models in production.
- Top Cited PapersOpen Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 3406-3416
Filtered-DiskANN: Graph Algorithms for Approximate Nearest Neighbor Search with Filters
As Approximate Nearest Neighbor Search (ANNS)-based dense retrieval becomes ubiquitous for search and recommendation scenarios, efficiently answering filtered ANNS queries has become a critical requirement. Filtered ANNS queries ask for the nearest neighbors of a query’s embedding from the points in the index that match the query’s labels such as date, price range, language. There has been little prior work on algorithms that use label metadata associated with vector data to build efficient indices for filtered ANNS queries. Consequently, current indices have high search latency or low recall which is not practical in interactive web-scenarios. We present two algorithms with native support for faster and more accurate filtered ANNS queries: one with streaming support, and another based on batch construction. Central to our algorithms is the construction of a graph-structured index which forms connections not only based on the geometry of the vector data, but also the associated label set. On real-world data with natural labels, both algorithms are an order of magnitude or more efficient for filtered queries than the current state of the art algorithms. The generated indices also be queried from an SSD and support thousands of queries per second at over [email protected].
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 3406-3416
Top Cited PapersOpen AccessFiltered-DiskANN: Graph Algorithms for Approximate Nearest Neighbor Search with Filters
As Approximate Nearest Neighbor Search (ANNS)-based dense retrieval becomes ubiquitous for search and recommendation scenarios, efficiently answering filtered ANNS queries has become a critical requirement. Filtered ANNS queries ask for the nearest neighbors of a query’s embedding from the points in the index that match the query’s labels such as date, price range, language. There has been little prior work on algorithms that use label metadata associated with vector data to build efficient indices for filtered ANNS queries. Consequently, current indices have high search latency or low recall which is not practical in interactive web-scenarios. We present two algorithms with native support for faster and more accurate filtered ANNS queries: one with streaming support, and another based on batch construction. Central to our algorithms is the construction of a graph-structured index which forms connections not only based on the geometry of the vector data, but also the associated label set. On real-world data with natural labels, both algorithms are an order of magnitude or more efficient for filtered queries than the current state of the art algorithms. The generated indices also be queried from an SSD and support thousands of queries per second at over [email protected].
- Open Access
- 27 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 258-266
NGAME: Negative Mining-aware Mini-batching for Extreme Classification
Extreme Classification (XC) seeks to tag data points with the most relevant subset of labels from an extremely large label set. Performing deep XC with dense, learnt representations for data points and labels has attracted much attention due to its superiority over earlier XC methods that used sparse, hand-crafted features. Negative mining techniques have emerged as a critical component of all deep XC methods, allowing them to scale to millions of labels. However, despite recent advances, training deep XC models with large encoder architectures such as transformers remains challenging. This paper notices that memory overheads of popular negative mining techniques often force mini-batch sizes to remain small and slow training down. In response, this paper introduces NGAME, a light-weight mini-batch creation technique that offers provably accurate in-batch negative samples. This allows training with larger mini-batches offering significantly faster convergence and higher accuracies than existing negative sampling techniques. NGAME was found to be up to 16% more accurate than state-of-the-art methods on a wide array of benchmark datasets for extreme classification, as well as 3% more accurate at retrieving search engine queries in response to a user webpage visit to show personalized ads. In live A/B tests on a popular search engine, NGAME yielded up to 23% gains in click-through-rates. Code for NGAME is available at https://github.com/Extreme-classification/ngame
- 27 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 258-266
Open AccessNGAME: Negative Mining-aware Mini-batching for Extreme Classification
Extreme Classification (XC) seeks to tag data points with the most relevant subset of labels from an extremely large label set. Performing deep XC with dense, learnt representations for data points and labels has attracted much attention due to its superiority over earlier XC methods that used sparse, hand-crafted features. Negative mining techniques have emerged as a critical component of all deep XC methods, allowing them to scale to millions of labels. However, despite recent advances, training deep XC models with large encoder architectures such as transformers remains challenging. This paper notices that memory overheads of popular negative mining techniques often force mini-batch sizes to remain small and slow training down. In response, this paper introduces NGAME, a light-weight mini-batch creation technique that offers provably accurate in-batch negative samples. This allows training with larger mini-batches offering significantly faster convergence and higher accuracies than existing negative sampling techniques. NGAME was found to be up to 16% more accurate than state-of-the-art methods on a wide array of benchmark datasets for extreme classification, as well as 3% more accurate at retrieving search engine queries in response to a user webpage visit to show personalized ads. In live A/B tests on a popular search engine, NGAME yielded up to 23% gains in click-through-rates. Code for NGAME is available at https://github.com/Extreme-classification/ngame