Showing posts with label machine learning. Show all posts
Showing posts with label machine learning. Show all posts

Tuesday, March 12, 2024

Quantum computing for finance: Our work is in UDaily.

 Great recent article in UDaily about our joint project with Argonne National Lab, JPMorgan Chase, Fujitsu and Menten AI. We discuss the obstacles and opportunities of quantum computing in finance.

Click here for the full article

Thursday, December 14, 2023

Ankit Kulshrestha's PhD Defense

Congratulations to Dr. Ankit Kulshrestha for successfully defending his Ph.D. thesis "A Machine Learning Approach To Improve Scalability and Robustness of Variational Quantum Circuits"! Ankit will join the quantum computing research group at Fujitsu Research USA.



Wednesday, December 29, 2021

Accelerating COVID-19 scientific discovery with hypothesis generation system

In 2020, the White House released the, “Call to Action to the Tech Community on New Machine Readable COVID-19 Dataset,” wherein artificial intelligence experts are asked to collect data and develop text mining techniques that can help the science community answer high-priority scientific questions related to COVID-19. The Allen Institute for AI and collaborators announced the availability of a rapidly growing open dataset of publications, the COVID-19 Open Research Dataset (CORD-19). As the pace of research accelerates, biomedical scientists struggle to stay current. To expedite their investigations, scientists leverage hypothesis generation systems, which can automatically inspect published papers to discover novel implicit connections. 

Ilya Tyagin, Ankit Kulshrestha, Justin Sybrandt, Krish Matta, Michael Shtutman, Ilya Safro "Accelerating COVID-19 research with graph mining and transformer-based learning", Innovative Applications of Artificial Intelligence (AAAI/IAAI), preprint at https://www.biorxiv.org/content/10.1101/2021.02.11.430789v1, 2022

We present an automated general purpose hypothesis generation systems AGATHA-C and AGATHA-GP for COVID-19 research. The systems are based on graph-mining and the transformer model. The systems are massively validated using retrospective information rediscovery and proactive analysis involving human-in-the-loop expert analysis. Both systems achieve high-quality predictions across domains (in some domains up to 0.97% ROC AUC) in fast computational time and are released to the broad scientific community to accelerate biomedical research. In addition, by performing the domain expert curated study, we show that the systems are able to discover on-going research findings such as the relationship between COVID-19 and oxytocin hormone.


Friday, November 6, 2020

On improving nonlinear SVM scalability using multilevel frameworks

Our paper "AML-SVM: Adaptive Multilevel Learning with Support Vector Machines" is accepted at 2020 IEEE International Conference on Big Data. https://arxiv.org/abs/2011.02592

The support vector machines (SVM) is one of the most widely used and practical optimization based classification models in machine learning because of its interpretability and flexibility to produce high quality results. However, the big data imposes a certain difficulty to the most sophisticated but relatively slow versions of SVM, namely, the nonlinear SVM. The complexity of nonlinear SVM solvers and the number of elements in the kernel matrix quadratically increases with the number of samples in training data. Therefore, both runtime and memory requirements are negatively affected. Moreover, the parameter fitting has extra kernel parameters to tune, which exacerbate the runtime even further. This paper proposes an adaptive multilevel learning framework for the nonlinear SVM, which addresses these challenges, improves the classification quality across the refinement process, and leverages multi-threaded parallel processing for better performance. The integration of parameter fitting in the hierarchical learning framework and adaptive process to stop unnecessary computation significantly reduce the running time while increase the overall performance. The experimental results demonstrate reduced variance on prediction over validation and test data across levels in the hierarchy, and significant speedup compared to state-of-the-art nonlinear SVM libraries without a decrease in the classification quality. 

Sunday, July 12, 2020

Two papers on graph representation learning

 Accepted papers at Workshop on Mining and Learning with Graphs co-located with ACM KDD 2020! 

1) Ding, Zhang, Sybrandt, Safro "Unsupervised Hierarchical Graph Representation Learning by Mutual Information Maximization", 2020

Graph representation learning based on graph neural networks (GNNs) can greatly improve the performance of downstream tasks, such as node and graph classification. However, the general GNN models do not aggregate node information in a hierarchical manner, and can miss key higher-order structural features of many graphs. The hierarchical aggregation also enables the graph representations to be explainable. In addition, supervised graph representation learning requires labeled data, which is expensive and error-prone. To address these issues, we present an unsupervised graph representation learning method, Unsupervised Hierarchical Graph Representation (UHGR), which can generate hierarchical representations of graphs. Our method focuses on maximizing mutual information between "local" and high-level "global" representations, which enables us to learn the node embeddings and graph embeddings without any labeled data. To demonstrate the effectiveness of the proposed method, we perform the node and graph classification using the learned node and graph embeddings. The results show that the proposed method achieves comparable results to state-of-the-art supervised methods on several benchmarks. In addition, our visualization of hierarchical representations indicates that our method can capture meaningful and interpretable clusters.

2) Sybrandt, Safro "FOBE and HOBE: First- and High-Order Bipartite Embeddings", 2020

Typical graph embeddings may not capture type-specific bipartite graph features that arise in such areas as recommender systems, data visualization, and drug discovery. Machine learning methods utilized in these applications would be better served with specialized embedding techniques. We propose two embeddings for bipartite graphs that decompose edges into sets of indirect relationships between node neighborhoods. When sampling higher-order relationships, we reinforce similarities through algebraic distance on graphs. We also introduce ensemble embeddings to combine both into a "best of both worlds" embedding. The proposed methods are evaluated on link prediction and recommendation tasks and compared with other state-of-the-art embeddings. While being all highly beneficial in applications, we demonstrate that none of the considered embeddings is clearly superior (in contrast to what is claimed in many papers), and discuss the trade offs present among them. 

Wednesday, February 19, 2020

New papers on biomedical NLP and hypothesis generation

New papers on biomedical NLP+hypothesis generation.

Sybrandt, Safro "CBAG: Conditional Biomedical Abstract Generation",  http://arxiv.org/pdf/2002.05637.pdf, 

Sybrandt, Tyagin, Shtutman, Safro "AGATHA: Automatic Graph-mining and Transformer based Hypothesis Generation" http://arxiv.org/pdf/2002.05635.pdf

Monday, April 29, 2019

Designing scalable nonlinear support vector machines

Accepted paper in Machine Learning journal 

Sadrfaridpour, Razzaghi, Safro, "Engineering fast multilevel support vector machines", 2019, preprint at https://arxiv.org/abs/1707.07657

The computational complexity of solving nonlinear support vector machine (SVM) is prohibitive on large-scale data. In particular, this issue becomes very sensitive when the data represents additional difficulties such as highly imbalanced class sizes. Typically, nonlinear kernels produce significantly higher classification quality to linear kernels but introduce extra kernel and model parameters which requires computationally expensive fitting. This increases the quality but also reduces the performance dramatically. We introduce a generalized fast multilevel framework for regular and weighted SVM and discuss several versions of its algorithmic components that lead to a good trade-off between quality and time. Our framework is implemented using PETSc which allows an easy integration with scientific computing tasks. The experimental results demonstrate significant speed up compared to the state-of-the-art nonlinear SVM libraries. 

Reproducibility: our source code, documentation and parameters are available at https://github.com/esadr/mlsvm

What we do/Team/In news

Quantum Computing     Quantum computers are expected to accelerate scientific discovery spanning many different areas such as medicine, AI, ...