Search Results for author: Vaibhav Rajan

Found 10 papers, 5 papers with code

Multi-Task Learning with User Preferences: Gradient Descent with Controlled Ascent in Pareto Optimization

1 code implementation ICML 2020 Debabrata Mahapatra, Vaibhav Rajan

However, they cannot be used to find exact Pareto optimal solutions satisfying user-specified preferences with respect to task-specific losses, that is not only a common requirement in applications but also a useful way to explore the infinite set of Pareto optimal solutions.

Multi-Task Learning

Exact Pareto Optimal Search for Multi-Task Learning: Touring the Pareto Front

no code implementations2 Aug 2021 Debabrata Mahapatra, Vaibhav Rajan

Addressing these requirements is challenging because it requires a search direction that allows descent not only towards the Pareto front but also towards the input preference, within the constraints imposed and in a manner that scales to high-dimensional gradients.

Decision Making Multi-Task Learning

Dont Just Divide; Polarize and Conquer!

1 code implementation23 Feb 2021 Shivin Srivastava, Siddharth Bhatia, Lingxiao Huang, Lim Jun Heng, Kenji Kawaguchi, Vaibhav Rajan

In data containing heterogeneous subpopulations, classification performance benefits from incorporating the knowledge of cluster structure in the classifier.

Classification General Classification

Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networks

no code implementations12 Feb 2021 Hansheng Xue, Luwei Yang, Vaibhav Rajan, Wen Jiang, Yi Wei, Yu Lin

A large number of network embedding methods exist to learn vectorial node representations from general graphs with both homogeneous and heterogeneous node and edge types, including some that can specifically model the distinct properties of bipartite networks.

Link Prediction Network Embedding +1

Multi-way Spectral Clustering of Augmented Multi-view Data through Deep Collective Matrix Tri-factorization

1 code implementation12 Sep 2020 Ragunathan Mariappan, Vaibhav Rajan

We present the first deep learning based architecture for collective matrix tri-factorization (DCMTF) of arbitrary collections of matrices, also known as augmented multi-view data.

Model-based Clustering using Automatic Differentiation: Confronting Misspecification and High-Dimensional Data

no code implementations8 Jul 2020 Siva Rajesh Kasa, Vaibhav Rajan

Our simulation studies show that EM has better clustering performance, measured by Adjusted Rand Index, compared to GD in cases of misspecification, whereas on high dimensional data GD outperforms EM.

Model Selection

Inferring Concept Prerequisite Relations from Online Educational Resources

1 code implementation30 Nov 2018 Sudeshna Roy, Meghana Madhyastha, Sheril Lawrence, Vaibhav Rajan

PREREQ can learn unknown concept prerequisites from course prerequisites and labeled concept prerequisite data.

Deep Collective Matrix Factorization for Augmented Multi-View Learning

no code implementations28 Nov 2018 Ragunathan Mariappan, Vaibhav Rajan

In this paper, we develop the first deep-learning based method, called dCMF, for unsupervised learning of multiple shared representations, that can model such non-linear interactions, from an arbitrary collection of matrices.


Cannot find the paper you are looking for? You can Submit a new open access paper.