1 code implementation • 13 May 2024 • Qi Chen, Xiubo Geng, Corby Rosset, Carolyn Buractaon, Jingwen Lu, Tao Shen, Kun Zhou, Chenyan Xiong, Yeyun Gong, Paul Bennett, Nick Craswell, Xing Xie, Fan Yang, Bryan Tower, Nikhil Rao, Anlei Dong, Wenqi Jiang, Zheng Liu, Mingqin Li, Chuanjie Liu, Zengzhong Li, Rangan Majumder, Jennifer Neville, Andy Oakley, Knut Magne Risvik, Harsha Vardhan Simhadri, Manik Varma, Yujing Wang, Linjun Yang, Mao Yang, Ce Zhang
Recent breakthroughs in large models have highlighted the critical significance of data scale, labels and modals.
no code implementations • 27 Feb 2024 • Corby Rosset, Ho-Lam Chung, Guanghui Qin, Ethan C. Chau, Zhuo Feng, Ahmed Awadallah, Jennifer Neville, Nikhil Rao
We show that users spend a lot of ``effort'' on these questions in terms of signals like clicks and session length, and that they are also challenging for GPT-4.
1 code implementation • 3 Oct 2023 • Canwen Xu, Corby Rosset, Ethan C. Chau, Luciano del Corro, Shweti Mahajan, Julian McAuley, Jennifer Neville, Ahmed Hassan Awadallah, Nikhil Rao
Remarkably, our automatic contrastive post-training further improves the performance of Orca, already a state-of-the-art instruction learning model tuned with GPT-4 outputs, to outperform ChatGPT.
no code implementations • 3 Oct 2023 • Guanghui Qin, Corby Rosset, Ethan C. Chau, Nikhil Rao, Benjamin Van Durme
For example, in the autoencoding task, Dodo shrinks context at a 20x compression ratio with a BLEU score of 98% for reconstruction, achieving nearly lossless encoding.
1 code implementation • 17 May 2023 • Jiong Zhu, Aishwarya Reganti, Edward Huang, Charles Dickens, Nikhil Rao, Karthik Subbian, Danai Koutra
Backed by our theoretical analysis, instead of maximizing the recovery of cross-instance node dependencies -- which has been considered the key behind closing the performance gap between model aggregation and centralized training -- , our framework leverages randomized assignment of nodes or super-nodes (i. e., collections of original nodes) to partition the training graph such that it improves data uniformity and minimizes the discrepancy of gradient and loss function across instances.
1 code implementation • 27 Feb 2023 • Wenqing Zheng, Edward W Huang, Nikhil Rao, Zhangyang Wang, Karthik Subbian
We identify this setting as Graph Intersection-induced Transfer Learning (GITL), which is motivated by practical applications in e-commerce or academic co-authorship predictions.
1 code implementation • 23 Nov 2022 • Yan Han, Edward W Huang, Wenqing Zheng, Nikhil Rao, Zhangyang Wang, Karthik Subbian
With these hyperedges, we augment the original bipartite graph into a new \textit{hypergraph}.
no code implementations • 6 Jul 2022 • Nurendra Choudhary, Nikhil Rao, Karthik Subbian, Chandan K. Reddy
In TESH-GCN, we extract semantic node information, which successively acts as a connection signal to extract relevant nodes' local neighborhood and graph-level metapath features from the sparse adjacency tensor in a reformulated hyperbolic graph convolution layer.
1 code implementation • 14 Jun 2022 • Chandan K. Reddy, Lluís Màrquez, Fran Valero, Nikhil Rao, Hugo Zaragoza, Sambaran Bandyopadhyay, Arnab Biswas, Anlu Xing, Karthik Subbian
This paper introduces the "Shopping Queries Dataset", a large dataset of difficult Amazon search queries and results, publicly released with the aim of fostering research in improving the quality of search results.
1 code implementation • 7 Jun 2022 • Weihua Hu, Rajas Bansal, Kaidi Cao, Nikhil Rao, Karthik Subbian, Jure Leskovec
We formalize the problem where the goal is for the embedding team to keep updating the embedding version, while the consumer teams do not have to retrain their models.
1 code implementation • 16 Feb 2022 • Yaochen Xie, Sumeet Katariya, Xianfeng Tang, Edward Huang, Nikhil Rao, Karthik Subbian, Shuiwang Ji
They are also unable to provide explanations in cases where the GNN is trained in a self-supervised manner, and the resulting representations are used in future downstream tasks.
2 code implementations • ICLR 2022 • Wenqing Zheng, Edward W Huang, Nikhil Rao, Sumeet Katariya, Zhangyang Wang, Karthik Subbian
We propose Cold Brew, a teacher-student distillation approach to address the SCS and noisy-neighbor challenges for GNNs.
no code implementations • 26 Oct 2021 • Reese Pathak, Rajat Sen, Nikhil Rao, N. Benjamin Erichson, Michael I. Jordan, Inderjit S. Dhillon
Our framework -- which we refer to as "cluster-and-conquer" -- is highly general, allowing for any time-series forecasting and clustering method to be used in each step.
1 code implementation • NeurIPS 2021 • Nurendra Choudhary, Nikhil Rao, Sumeet Katariya, Karthik Subbian, Chandan K. Reddy
Current approaches employ spatial geometries such as boxes to learn query representations that encompass the answer entities and model the logical operations of projection and intersection.
no code implementations • 29 Sep 2021 • Yaochen Xie, Sumeet Katariya, Xianfeng Tang, Edward W Huang, Nikhil Rao, Karthik Subbian, Shuiwang Ji
TAGE enables the explanation of GNN embedding models without downstream tasks and allows efficient explanation of multitask models.
no code implementations • 5 Sep 2021 • Cuize Han, Nikhil Rao, Daria Sorokina, Karthik Subbian
Gradient Boosted Decision Trees (GBDTs) are widely used for building ranking and relevance models in search and recommendation.
1 code implementation • 2 Aug 2021 • Parth K. Thaker, Mohit Malu, Nikhil Rao, Gautam Dasarathy
In this paper, we consider the pure exploration problem in stochastic multi-armed bandits where the similarities between the arms are captured by a graph and the rewards may be represented as a smooth signal on this graph.
1 code implementation • 23 Dec 2020 • Nurendra Choudhary, Nikhil Rao, Sumeet Katariya, Karthik Subbian, Chandan K. Reddy
Promising approaches to tackle this problem include embedding the KG units (e. g., entities and relations) in a Euclidean space such that the query embedding contains the information relevant to its results.
no code implementations • COLING 2020 • Kshitij Tayal, Nikhil Rao, Saurabh Agarwal, Xiaowei Jia, Karthik Subbian, Vipin Kumar
The lack of structure in short text sequences limits the success of popular NLP methods based on deep learning.
no code implementations • ACL 2020 • Thanh V. Nguyen, Nikhil Rao, Karthik Subbian
Showing items that do not match search query intent degrades customer experience in e-commerce.
no code implementations • 29 May 2019 • Liwei Wu, Hsiang-Fu Yu, Nikhil Rao, James Sharpnack, Cho-Jui Hsieh
In this paper, we propose using Graph DNA, a novel Deep Neighborhood Aware graph encoding algorithm, for exploiting deeper neighborhood information.
2 code implementations • 6 Jul 2017 • Yifan Sun, Nikhil Rao, Weicong Ding
Evaluating these methods is also problematic, as rigorous quantitative evaluations in this space is limited, especially when compared with single-sense embeddings.
no code implementations • 4 May 2017 • Vatsal Shah, Nikhil Rao, Weicong Ding
While there has been recent research on incorporating explicit side information in the low-rank matrix factorization setting, often implicit information can be gleaned from the data, via higher-order interactions among entities.
2 code implementations • 2 Mar 2017 • Zijun Yao, Yifan Sun, Weicong Ding, Nikhil Rao, Hui Xiong
Word evolution refers to the changing meanings and associations of words throughout time, as a byproduct of human language evolution.
no code implementations • NeurIPS 2016 • Prateek Jain, Nikhil Rao, Inderjit S. Dhillon
Several learning applications require solving high-dimensional regression problems where the relevant features belong to a small number of (overlapping) groups.
no code implementations • NeurIPS 2016 • Hsiang-Fu Yu, Nikhil Rao, Inderjit S. Dhillon
We develop novel regularization schemes and use scalable matrix factorization methods that are eminently suited for high-dimensional time series data that has many missing values.
no code implementations • 13 Mar 2016 • Nikhil Rao, Ravi Ganti, Laura Balzano, Rebecca Willett, Robert Nowak
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 combination of features.
no code implementations • 19 Feb 2016 • 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.
no code implementations • NeurIPS 2015 • Parikshit Shah, Nikhil Rao, Gongguo Tang
Our method relies on a reduction of the problem to sparse and low-rank matrix decomposition via the notion of tensor contraction.
2 code implementations • NeurIPS 2015 • Nikhil Rao, Hsiang-Fu Yu, Pradeep K. Ravikumar, Inderjit S. Dhillon
Low rank matrix completion plays a fundamental role in collaborative filtering applications, the key idea being that the variables lie in a smaller subspace than the ambient space.
Ranked #1 on
Recommendation Systems
on Flixster
(using extra training data)
no code implementations • 28 Sep 2015 • Hsiang-Fu Yu, Nikhil Rao, Inderjit S. Dhillon
High-dimensional time series prediction is needed in applications as diverse as demand forecasting and climatology.
no code implementations • 30 Jun 2015 • Ravi Ganti, Nikhil Rao, Rebecca M. Willett, Robert Nowak
Single Index Models (SIMs) are simple yet flexible semi-parametric models for classification and regression.
no code implementations • 15 May 2015 • Parikshit Shah, Nikhil Rao, Gongguo Tang
This motivates us to consider the problem of low rank tensor recovery from a class of linear measurements called separable measurements.
no code implementations • 23 Apr 2014 • Nikhil Rao, Parikshit Shah, Stephen Wright
CoGEnT combines a greedy selection scheme based on the conditional gradient approach with a backward (or "truncation") step that exploits the quadratic nature of the objective to reduce the basis size.
no code implementations • 18 Feb 2014 • Nikhil Rao, Robert Nowak, Christopher Cox, Timothy Rogers
In this paper, we are interested in a less restrictive form of structured sparse feature selection: we assume that while features can be grouped according to some notion of similarity, not all features in a group need be selected for the task at hand.
no code implementations • NeurIPS 2013 • Nikhil Rao, Christopher Cox, Robert Nowak, Timothy Rogers
In this paper, we are interested in a less restrictive form of multitask learning, wherein (1) the available features can be organized into subsets according to a notion of similarity and (2) features useful in one task are similar, but not necessarily identical, to the features best suited for other tasks.