Ninh Pham
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
Research Subjects
Ninh Pham has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Rasmus Pagh
BARC, University of Copenhagen, Copenhagen, Denmark
5 shared publications - Francesco Silvestri
University of Padova
3 shared publications Quang Loc Le
2 shared publications- Tran Khanh Dang
Van Lang University
2 shared publications - Gillian Dobbie
University of Auckland
1 shared publication Hoang Thanh Lam
1 shared publication
Latest Publications
- 11 October 2026
- Published by Springer Nature
- p. 480-488
SISAP Indexing Challenge 2026 Solution for Task 1: Accelerating NNDescent with LSH
- 11 October 2026
- Published by Springer Nature
- p. 480-488
SISAP Indexing Challenge 2026 Solution for Task 1: Accelerating NNDescent with LSH
- Open Access
Scalable Varied-Density Clustering via Graph Propagation
We propose a novel perspective on varied-density clustering for high-dimensional data by framing it as a label propagation process in neighborhood graphs that adapt to local density variations. Our method formally connects density-based clustering with graph connectivity, enabling the use of efficient graph propagation techniques developed in network science. To ensure scalability, we introduce a density-aware neighborhood propagation algorithm and leverage advanced random projection methods to construct approximate neighborhood graphs. Our approach significantly reduces computational cost while preserving clustering quality. Empirically, it scales to datasets with millions of points in minutes and achieves competitive accuracy compared to existing baselines.
Open AccessScalable Varied-Density Clustering via Graph Propagation
We propose a novel perspective on varied-density clustering for high-dimensional data by framing it as a label propagation process in neighborhood graphs that adapt to local density variations. Our method formally connects density-based clustering with graph connectivity, enabling the use of efficient graph propagation techniques developed in network science. To ensure scalability, we introduce a density-aware neighborhood propagation algorithm and leverage advanced random projection methods to construct approximate neighborhood graphs. Our approach significantly reduces computational cost while preserving clustering quality. Empirically, it scales to datasets with millions of points in minutes and achieves competitive accuracy compared to existing baselines.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (11) , 11590-11597
On Finding Hubs in High Dimensions with Sampling
Hubs are a few points that frequently appear in the k-nearest neighbors (kNN) of many other points in a high-dimensional data set. The hubs' effects, called the hubness phenomenon, degrade the performance of kNN based models in high dimensions. We present SamHub, a simple sampling approach to efficiently identify hubs with theoretical guarantees. Apart from previous works based on approximate kNN indexes, SamHub is generic and applicable to any distance measure with negligible additional memory footprint. Empirically, by sampling only 10% of points, SamHub runs significantly faster and offers higher accuracy than existing hub detection methods on many real-world data sets with dot product, L1, L2, and dynamic time warping distances. Our ablation studies of SamHub on improving kNN-based classification show potential for other high-dimensional data analysis tasks.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (11) , 11590-11597
Open AccessOn Finding Hubs in High Dimensions with Sampling
Hubs are a few points that frequently appear in the k-nearest neighbors (kNN) of many other points in a high-dimensional data set. The hubs' effects, called the hubness phenomenon, degrade the performance of kNN based models in high dimensions. We present SamHub, a simple sampling approach to efficiently identify hubs with theoretical guarantees. Apart from previous works based on approximate kNN indexes, SamHub is generic and applicable to any distance measure with negligible additional memory footprint. Empirically, by sampling only 10% of points, SamHub runs significantly faster and offers higher accuracy than existing hub detection methods on many real-world data sets with dot product, L1, L2, and dynamic time warping distances. Our ablation studies of SamHub on improving kNN-based classification show potential for other high-dimensional data analysis tasks.
- 12 February 2024
- Published by Springer Nature
- p. 394-407
On Deploying Mobile Deep Learning to Segment COVID-19 PCR Test Tube Images
- 12 February 2024
- Published by Springer Nature
- p. 394-407
On Deploying Mobile Deep Learning to Segment COVID-19 PCR Test Tube Images
- 17 September 2023
- Published by Springer Nature
- p. 286-301
A Transductive Forest for Anomaly Detection with Few Labels
- 17 September 2023
- Published by Springer Nature
- p. 286-301
A Transductive Forest for Anomaly Detection with Few Labels
- Open Access
Falconn++: A Locality-sensitive Filtering Approach for Approximate Nearest Neighbor Search
We present Falconn++, a novel locality-sensitive filtering approach for approximate nearest neighbor search on angular distance. Falconn++ can filter out potential far away points in any hash bucket \textit{before} querying, which results in higher quality candidates compared to other hashing-based solutions. Theoretically, Falconn++ asymptotically achieves lower query time complexity than Falconn, an optimal locality-sensitive hashing scheme on angular distance. Empirically, Falconn++ achieves higher recall-speed tradeoffs than Falconn on many real-world data sets. Falconn++ is also competitive with HNSW, an efficient representative of graph-based solutions on high search recall regimes.
Open AccessFalconn++: A Locality-sensitive Filtering Approach for Approximate Nearest Neighbor Search
We present Falconn++, a novel locality-sensitive filtering approach for approximate nearest neighbor search on angular distance. Falconn++ can filter out potential far away points in any hash bucket \textit{before} querying, which results in higher quality candidates compared to other hashing-based solutions. Theoretically, Falconn++ asymptotically achieves lower query time complexity than Falconn, an optimal locality-sensitive hashing scheme on angular distance. Empirically, Falconn++ achieves higher recall-speed tradeoffs than Falconn on many real-world data sets. Falconn++ is also competitive with HNSW, an efficient representative of graph-based solutions on high search recall regimes.
- Open Access
Sublinear Maximum Inner Product Search using Concomitants of Extreme Order Statistics
We propose a novel dimensionality reduction method for maximum inner product search (MIPS), named CEOs, based on the theory of concomitants of extreme order statistics. Utilizing the asymptotic behavior of these concomitants, we show that a few dimensions associated with the extreme values of the query signature are enough to estimate inner products. Since CEOs only uses the sign of a small subset of the query signature for estimation, we can precompute all inner product estimators accurately before querying. These properties yield a sublinear MIPS algorithm with an exponential indexing space complexity. We show that our exponential space is optimal for the $(1 + \epsilon)$-approximate MIPS on a unit sphere. The search recall of CEOs can be theoretically guaranteed under a mild condition. To deal with the exponential space complexity, we propose two practical variants, including sCEOs-TA and coCEOs, that use linear space for solving MIPS. sCEOs-TA exploits the threshold algorithm (TA) and provides superior search recalls to competitive MIPS solvers. coCEOs is a data and dimension co-reduction technique and outperforms sCEOs-TA on high recall requirements. Empirically, they are very simple to implement and achieve at least 100x speedup compared to the bruteforce search while returning top-10 MIPS with accuracy at least 90% on many large-scale data sets.
Open AccessSublinear Maximum Inner Product Search using Concomitants of Extreme Order Statistics
We propose a novel dimensionality reduction method for maximum inner product search (MIPS), named CEOs, based on the theory of concomitants of extreme order statistics. Utilizing the asymptotic behavior of these concomitants, we show that a few dimensions associated with the extreme values of the query signature are enough to estimate inner products. Since CEOs only uses the sign of a small subset of the query signature for estimation, we can precompute all inner product estimators accurately before querying. These properties yield a sublinear MIPS algorithm with an exponential indexing space complexity. We show that our exponential space is optimal for the $(1 + \epsilon)$-approximate MIPS on a unit sphere. The search recall of CEOs can be theoretically guaranteed under a mild condition. To deal with the exponential space complexity, we propose two practical variants, including sCEOs-TA and coCEOs, that use linear space for solving MIPS. sCEOs-TA exploits the threshold algorithm (TA) and provides superior search recalls to competitive MIPS solvers. coCEOs is a data and dimension co-reduction technique and outperforms sCEOs-TA on high recall requirements. Empirically, they are very simple to implement and achieve at least 100x speedup compared to the bruteforce search while returning top-10 MIPS with accuracy at least 90% on many large-scale data sets.
- 25 February 2021
- Published by Springer Nature
- p. 439-455
Revisiting Wedge Sampling for Budgeted Maximum Inner Product Search
- 25 February 2021
- Published by Springer Nature
- p. 439-455
Revisiting Wedge Sampling for Budgeted Maximum Inner Product Search
- Open Access
Revisiting Wedge Sampling for Budgeted Maximum Inner Product Search
Top-k maximum inner product search (MIPS) is a central task in many machine learning applications. This paper extends top-k MIPS with a budgeted setting, that asks for the best approximate top-k MIPS given a limit of B computational operations. We investigate recent advanced sampling algorithms, including wedge and diamond sampling to solve it. Though the design of these sampling schemes naturally supports budgeted top-k MIPS, they suffer from the linear cost from scanning all data points to retrieve top-k results and the performance degradation for handling negative inputs. This paper makes two main contributions. First, we show that diamond sampling is essentially a combination between wedge sampling and basic sampling for top-k MIPS. Our theoretical analysis and empirical evaluation show that wedge is competitive (often superior) to diamond on approximating top-k MIPS regarding both efficiency and accuracy. Second, we propose a series of algorithmic engineering techniques to deploy wedge sampling on budgeted top-k MIPS. Our novel deterministic wedge-based algorithm runs significantly faster than the state-of-the-art methods for budgeted and exact top-k MIPS while maintaining the top-5 precision at least 80% on standard recommender system data sets.
Open AccessRevisiting Wedge Sampling for Budgeted Maximum Inner Product Search
Top-k maximum inner product search (MIPS) is a central task in many machine learning applications. This paper extends top-k MIPS with a budgeted setting, that asks for the best approximate top-k MIPS given a limit of B computational operations. We investigate recent advanced sampling algorithms, including wedge and diamond sampling to solve it. Though the design of these sampling schemes naturally supports budgeted top-k MIPS, they suffer from the linear cost from scanning all data points to retrieve top-k results and the performance degradation for handling negative inputs. This paper makes two main contributions. First, we show that diamond sampling is essentially a combination between wedge sampling and basic sampling for top-k MIPS. Our theoretical analysis and empirical evaluation show that wedge is competitive (often superior) to diamond on approximating top-k MIPS regarding both efficiency and accuracy. Second, we propose a series of algorithmic engineering techniques to deploy wedge sampling on budgeted top-k MIPS. Our novel deterministic wedge-based algorithm runs significantly faster than the state-of-the-art methods for budgeted and exact top-k MIPS while maintaining the top-5 precision at least 80% on standard recommender system data sets.
- 18 January 2019
- Published by Springer Nature
- p. 105-121
L1-Depth Revisited: A Robust Angle-Based Outlier Factor in High-Dimensional Space
- 18 January 2019
- Published by Springer Nature
- p. 105-121
L1-Depth Revisited: A Robust Angle-Based Outlier Factor in High-Dimensional Space