109 citations · 457 across the 29 of their papers we have counts for
30 papers
Multi-ResNets for Subspace Preconditioning in Constrained Optimization
Merve Karakas, Christopher J. Williams, Emmanuel O. Balogun +3
We propose MResOpt, a staged residual neural network architecture for constrained optimization problems. Our architecture fits within predict-complete-correct pipelines and decompo…
Simplifying Distributed Neural Network Training on Massive Graphs: Randomized Partitions Improve Model Aggregation
Jiong Zhu, Aishwarya Reganti, Edward Huang +4
Distributed training of GNNs enables learning on massive graphs (e.g., social and e-commerce networks) that exceed the storage and computational capacity of a single machine. To re…
You Only Transfer What You Share: Intersection-Induced Graph Transfer Learning for Link Prediction
Wenqing Zheng, Edward W Huang, Nikhil Rao +2
Link prediction is central to many real-world applications, but its performance may be hampered when the graph of interest is sparse. To alleviate issues caused by sparsity, we inv…
Search Behavior Prediction: A Hypergraph Perspective
Yan Han, Edward W Huang, Wenqing Zheng +3
Although the bipartite shopping graphs are straightforward to model search behavior, they suffer from two challenges: 1) The majority of items are sporadically searched and hence h…
Text Enriched Sparse Hyperbolic Graph Convolutional Networks
Nurendra Choudhary, Nikhil Rao, Karthik Subbian +1
Heterogeneous networks, which connect informative nodes containing text with different edge types, are routinely used to store and process information in various real-world applica…
Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search
Chandan K. Reddy, Lluís Màrquez, Fran Valero +6
Improving the quality of search results can significantly enhance users experience and engagement with search engines. In spite of several recent advancements in the fields of mach…
Learning Backward Compatible Embeddings
Weihua Hu, Rajas Bansal, Kaidi Cao +3
Embeddings, low-dimensional vector representation of objects, are fundamental in building modern machine learning systems. In industrial settings, there is usually an embedding tea…
Task-Agnostic Graph Explanations
Yaochen Xie, Sumeet Katariya, Xianfeng Tang +4
Graph Neural Networks (GNNs) have emerged as powerful tools to encode graph-structured data. Due to their broad applications, there is an increasing need to develop tools to explai…
Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods
Wenqing Zheng, Edward W Huang, Nikhil Rao +3
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in node classification, regression, and recommendation tasks. GNNs work well when rich and high-quality conn…
Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs
Nurendra Choudhary, Nikhil Rao, Sumeet Katariya +2
Logical reasoning over Knowledge Graphs (KGs) is a fundamental technique that can provide efficient querying mechanism over large and incomplete databases. Current approaches emplo…
Cluster-and-Conquer: A Framework For Time-Series Forecasting
Reese Pathak, Rajat Sen, Nikhil Rao +3
We propose a three-stage framework for forecasting high-dimensional time-series data. Our method first estimates parameters for each univariate time series. Next, we use these para…
Scalable Feature Selection for (Multitask) Gradient Boosted Trees
Cuize Han, Nikhil Rao, Daria Sorokina +1
Gradient Boosted Decision Trees (GBDTs) are widely used for building ranking and relevance models in search and recommendation. Considerations such as latency and interpretability…
Maximizing and Satisficing in Multi-armed Bandits with Graph Information
Parth K. Thaker, Mohit Malu, Nikhil Rao +1
Pure exploration in multi-armed bandits has emerged as an important framework for modeling decision-making and search under uncertainty. In modern applications, however, one is oft…
Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs
Nurendra Choudhary, Nikhil Rao, Sumeet Katariya +2
Knowledge Graphs (KGs) are ubiquitous structures for information storagein several real-world applications such as web search, e-commerce, social networks, and biology. Querying KG…
Learning Robust Models for e-Commerce Product Search
Thanh V. Nguyen, Nikhil Rao, Karthik Subbian
Showing items that do not match search query intent degrades customer experience in e-commerce. These mismatches result from counterfactual biases of the ranking algorithms toward…
Graph DNA: Deep Neighborhood Aware Graph Encoding for Collaborative Filtering
Liwei Wu, Hsiang-Fu Yu, Nikhil Rao +2
In this paper, we consider recommender systems with side information in the form of graphs. Existing collaborative filtering algorithms mainly utilize only immediate neighborhood i…
A Simple Approach to Learn Polysemous Word Embeddings
Yifan Sun, Nikhil Rao, Weicong Ding
Many NLP applications require disambiguating polysemous words. Existing methods that learn polysemous word vector representations involve first detecting various senses and optimiz…
Matrix Completion via Factorizing Polynomials
Vatsal Shah, Nikhil Rao, Weicong Ding
Predicting unobserved entries of a partially observed matrix has found wide applicability in several areas, such as recommender systems, computational biology, and computer vision.…
Dynamic Word Embeddings for Evolving Semantic Discovery
Zijun Yao, Yifan Sun, Weicong Ding +2
Word evolution refers to the changing meanings and associations of words throughout time, as a byproduct of human language evolution. By studying word evolution, we can infer socia…
On Learning High Dimensional Structured Single Index Models
Nikhil Rao, Ravi Ganti, Laura Balzano +2
Single Index Models (SIMs) are simple yet flexible semi-parametric models for machine learning, where the response variable is modeled as a monotonic function of a linear combinati…
Structured Sparse Regression via Greedy Hard-Thresholding
Prateek Jain, Nikhil Rao, Inderjit Dhillon
Several learning applications require solving high-dimensional regression problems where the relevant features belong to a small number of (overlapping) groups. For very large data…
High-dimensional Time Series Prediction with Missing Values
Hsiang-Fu Yu, Nikhil Rao, Inderjit S. Dhillon
High-dimensional time series prediction is needed in applications as diverse as demand forecasting and climatology. Often, such applications require methods that are both highly sc…
Learning Single Index Models in High Dimensions
Ravi Ganti, Nikhil Rao, Rebecca M. Willett +1
Single Index Models (SIMs) are simple yet flexible semi-parametric models for classification and regression. Response variables are modeled as a nonlinear, monotonic function of a…
Optimal Low-Rank Tensor Recovery from Separable Measurements: Four Contractions Suffice
Parikshit Shah, Nikhil Rao, Gongguo Tang
Tensors play a central role in many modern machine learning and signal processing applications. In such applications, the target tensor is usually of low rank, i.e., can be express…