Privacy Enhancement for Cloud-Based Few-Shot Learning

1 code implementation • 10 May 2022 • Archit Parnami, Muhammad Usama, Liyue Fan, Minwoo Lee

Requiring less data for accurate models, few-shot learning has shown robustness and generality in many application domains.

Few-Shot Image Classification Few-Shot Learning

Learning from Few Examples: A Summary of Approaches to Few-Shot Learning

no code implementations • 7 Mar 2022 • Archit Parnami, Minwoo Lee

Few-Shot Learning refers to the problem of learning the underlying pattern in the data just from a few training samples.

Few-Shot Learning Transfer Learning

Transformation of Node to Knowledge Graph Embeddings for Faster Link Prediction in Social Networks

1 code implementation • 17 Nov 2021 • Archit Parnami, Mayuri Deshpande, Anant Kumar Mishra, Minwoo Lee

Two techniques which we focus on in this work are 1) node embeddings from random walk based methods and 2) knowledge graph embeddings.

Knowledge Graph Embeddings Link Prediction +2

Pruning Attention Heads of Transformer Models Using A* Search: A Novel Approach to Compress Big NLP Architectures

no code implementations • 28 Oct 2021 • Archit Parnami, Rahul Singh, Tarun Joshi

Our results indicate that the method could eliminate as much as 40% of the attention heads in the BERT transformer model with no loss in accuracy.

Few-Shot Keyword Spotting With Prototypical Networks

1 code implementation • arXiv 2020 • Archit Parnami, Minwoo Lee

Recognizing a particular command or a keyword, keyword spotting has been widely used in many voice interfaces such as Amazon's Alexa and Google Home.

Keyword Spotting Metric Learning