Search Results for author: Manohar Kaul

Found 15 papers, 8 papers with code

BERTops: Studying BERT Representations under a Topological Lens

1 code implementation2 May 2022 Jatin Chauhan, Manohar Kaul

Proposing scoring functions to effectively understand, analyze and learn various properties of high dimensional hidden representations of large-scale transformer models like BERT can be a challenging task.

Adversarial Attack

ALLWAS: Active Learning on Language models in WASserstein space

no code implementations3 Sep 2021 Anson Bastos, Manohar Kaul

Language models have emerged as the prevalent choice of several natural language tasks due to the performance boost offered by these models.

Active Learning text-classification +1

Target Model Agnostic Adversarial Attacks with Query Budgets on Language Understanding Models

no code implementations13 Jun 2021 Jatin Chauhan, Karan Bhukar, Manohar Kaul

Despite significant improvements in natural language understanding models with the advent of models like BERT and XLNet, these neural-network based classifiers are vulnerable to blackbox adversarial attacks, where the attacker is only allowed to query the target model outputs.

Adversarial Attack Natural Language Understanding

Understanding Higher-order Structures in Evolving Graphs: A Simplicial Complex based Kernel Estimation Approach

no code implementations6 Feb 2021 Manohar Kaul, Masaaki Imaizumi

In this paper, we overcome these obstacles by capturing higher-order interactions succinctly as \textit{simplices}, model their neighborhood by face-vectors, and develop a nonparametric kernel estimator for simplices that views the evolving graph from the perspective of a time process (i. e., a sequence of graph snapshots).

Link Prediction

Higher-order Structure Prediction in Evolving Graph Simplicial Complexes

no code implementations1 Jan 2021 Manohar Kaul, Masaaki Imaizumi

In this paper, we overcome these obstacles by capturing higher-order interactions succinctly as simplices, model their neighborhood by face-vectors, and develop a nonparametric kernel estimator for simplices that views the evolving graph from the perspective of a time process (i. e., a sequence of graph snapshots).

Link Prediction

Self-Supervised Few-Shot Learning on Point Clouds

1 code implementation NeurIPS 2020 Charu Sharma, Manohar Kaul

We present a comprehensive empirical evaluation of our method on both downstream classification and segmentation tasks and show that supervised methods pre-trained with our self-supervised learning method significantly improve the accuracy of state-of-the-art methods.

Few-Shot Learning General Classification +2

A Weighted Quiver Kernel using Functor Homology

no code implementations27 Sep 2020 Manohar Kaul, Dai Tamaki

Our model of such networks is a directed graph $Q$ equipped with a weight function $w$ on the set $Q_{1}$ of arrows in $Q$.

Simplicial Complex based Point Correspondence between Images warped onto Manifolds

1 code implementation ECCV 2020 Charu Sharma, Manohar Kaul

Recent increase in the availability of warped images projected onto a manifold (e. g., omnidirectional spherical images), coupled with the success of higher-order assignment methods, has sparked an interest in the search for improved higher-order matching algorithms on warped images due to projection.

Hypergraph Matching

Learning Representations using Spectral-Biased Random Walks on Graphs

1 code implementation19 May 2020 Charu Sharma, Jatin Chauhan, Manohar Kaul

Several state-of-the-art neural graph embedding methods are based on short random walks (stochastic processes) because of their ease of computation, simplicity in capturing complex local graph properties, scalability, and interpretibility.

Graph Embedding Link Prediction +1

Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures

1 code implementation ICLR 2020 Jatin Chauhan, Deepak Nathani, Manohar Kaul

We propose to study the problem of few shot graph classification in graph neural networks (GNNs) to recognize unseen classes, given limited labeled graph examples.

Active Learning Classification +3

Solving Partial Assignment Problems using Random Clique Complexes

1 code implementation ICML 2018 Charu Sharma, Deepak Nathani, Manohar Kaul

We present an alternate formulation of the partial assignment problem as matching random clique complexes, that are higher-order analogues of random graphs, designed to provide a set of invariants that better detect higher-order structure.

Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs

2 code implementations ACL 2019 Deepak Nathani, Jatin Chauhan, Charu Sharma, Manohar Kaul

The recent proliferation of knowledge graphs (KGs) coupled with incomplete or partial information, in the form of missing relations (links) between entities, has fueled a lot of research on knowledge base completion (also known as relation prediction).

Knowledge Base Completion Knowledge Graph Embeddings +1

Using Incomplete Information for Complete Weight Annotation of Road Networks -- Extended Version

no code implementations2 Aug 2013 Bin Yang, Manohar Kaul, Christian S. Jensen

This paper formulates and addresses the problem of annotating all edges in a road network with travel cost based weights from a set of trips in the network that cover only a small fraction of the edges, each with an associated ground-truth travel cost.

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