Skip to main content

Javed Aslam

Professor

Senior Associate Dean - Academic Affairs

Javed Aslam

Contact

WPersonal site

GGoogle Scholar

Ejaa@ccs.neu.edu

T617.373.8169

Office Location

440 Huntington Avenue
246 West Village H
Boston, MA 02115

Mailing Address

Northeastern University
ATTN: Javed Aslam, 202 WVH
360 Huntington Avenue
Boston, Massachusetts 02115

Research Interests

  • Machine learning
  • Information retrieval
  • Applications of statistics and information theory

Education

  • PhD in Computer Science, Massachusetts Institute of Technology
  • MS in Computer Science, Massachusetts Institute of Technology
  • BS in Electrical Engineering, University of Notre Dame

Biography

Javed Aslam is a Professor and Senior Associate Dean for Academic Affairs at the Khoury College of Computer Sciences at Northeastern University. Prior to joining Northeastern University, he was an assistant professor in the Department of Computer Science at Dartmouth College. Professor Aslam has also held a postdoctoral position in the School of Engineering and Applied Sciences at Harvard University. Professor Aslam received his BS in Electrical Engineering from the University of Notre Dame and his PhD in Computer Science from MIT.

Professor Aslam’s research interests include machine learning, information retrieval, and the design and analysis of algorithms. In machine learning, he has developed models and algorithms for multi-label classification and for learning in the presence of noisy or erroneous training data. In information retrieval, he applied techniques from machine learning, statistics, information theory, and social choice theory to develop algorithms for automatic information organization, metasearch, and efficient search engine training and evaluation. He has also been involved in the fields of human computation, transportation, computer security, wireless networking, and medical informatics. Prof. Aslam served as the General co-Chair for the 2009 ACM SIGIR Conference on Research and Development in Information Retrieval, and he also served as the Program co-Chair for SIGIR 2016.

 

Projects

Recent Publications

Scaling Up Ordinal Embedding: A Landmark Approach

Anderton, J. & Aslam, J.. (2019). Scaling Up Ordinal Embedding: A Landmark Approach. Proceedings of the 36th International Conference on Machine Learning, in PMLR 97:282-290

Abstract

Ordinal Embedding is the problem of placing n objects into R^ d to satisfy constraints like “object a is closer to b than to c.” It can accommodate data that embeddings from features or distances cannot, but is a more difficult problem. We propose a novel landmark-based method as a partial solution. At small to medium scales, we present a novel combination of existing methods with some new theoretical justification. For very large values of n optimizing over an entire embedding breaks down, so we propose a novel method which first embeds a subset of m<< n objects and then embeds the remaining objects independently and in parallel. We prove a distance error bound for our method in terms of m and that it has O (dn log m) time complexity, and show empirically that it is able to produce high quality embeddings in a fraction of the time needed for any published method.

Adapting RNN Sequence Prediction Model to Multi-label Set Prediction

Conference Proceedings Adapting RNN Sequence Prediction Model to Multi-label Set Prediction. Qin, Kechen; Li, Cheng; Pavlu, Virgil; Aslam, Javed. Proceedings of the 2019 NAACL-HLT, Volume 1 (Long and Short Papers), 2019 8 jun I Association for Computational Linguistics, Minneapolis, Minnesota

Abstract

We present an adaptation of RNN sequence models to the problem of multi-label classification for text, where the target is a set of labels, not a sequence. Previous such RNN models define probabilities for sequences but not for sets; attempts to obtain a set probability are after-thoughts of the network design, including pre-specifying the label order, or relating the sequence probability to the set probability in ad hoc ways. Our formulation is derived from a principled notion of set probability, as the sum of probabilities of corresponding permutation sequences for the set. We provide a new training objective that maximizes this set probability, and a new prediction objective that finds the most probable set on a test document. These new objectives are theoretically appealing because they give the RNN model freedom to discover the best label order, which often is the natural one (but different among documents). We develop efficient procedures to tackle the computation difficulties involved in training and prediction. Experiments on benchmark datasets demonstrate that we outperform state-of-the-art methods for this task.

A Pipeline for Optimizing F1-Measure in Multi-label Text Classification

B. Wang, C. Li, V. Pavlu, J. Aslam, "A Pipeline for Optimizing F1-Measure in Multi-label Text Classification ," ICMLA, 2018.

Abstract

Multi-label text classification is the machine learning task wherein each document is tagged with multiple labels, and this task is uniquely challenging due to high dimensional features and correlated labels. Such text classifiers need to be regularized to prevent severe over-fitting in the high dimensional space, and they also need to take into account label dependencies in order to make accurate predictions under uncertainty. Many classic multi-label learning algorithms focus on incorporating label dependencies in the model training phase and optimize for the strict set-accuracy measure. We propose a new pipeline which takes such algorithms and improves their F1-performance with careful training regularization and a new prediction strategy based on support inference, calibration and GFM, to the point that classic multi-label models are able to outperform recent sophisticated methods (PDsparse, SPEN) and models (LSF, CFT, CLEMS) designed specifically to be multi-label F-optimal. Beyond performance and practical contributions, we further demonstrate that support inference acts as a strong regularizer on the label prediction structure.

Previous Publications

2018

Pure Exploration in Infinitely-Armed Bandit Models with Fixed-Confidence

Pure Exploration in Infinitely-Armed Bandit Models with Fixed-Confidence. Maryam Aziz, Jesse Anderton, Emilie Kaufmann and Javed Aslam. ALT 2018.

Abstract

We consider the problem of near-optimal arm identification in the fixed confidence setting of the infinitely armed bandit problem when nothing is known about the arm reservoir distribution. We (1) introduce a PAC-like framework within which to derive and cast results; (2) derive a sample complexity lower bound for near-optimal arm identification; (3) propose an algorithm that identifies a nearly-optimal arm with high probability and derive an upper bound on its sample complexity which is within a log factor of our lower bound; and (4) discuss whether our log^2(1/delta) dependence is inescapable for “two-phase” (select arms first, identify the best later) algorithms in the infinite setting. This work permits the application of bandit models to a broader class of problems where fewer assumptions hold.

Related News

CCIS Alumna takes Northeastern lessons to University College London

Professor Builds on His Role as a Faculty Leader

Khoury PhD Students & Post-Docs

Past PhD Students & Post-Docs