papers

Publications (8)

cs.LG2019

Hyperbolic Graph Convolutional Neural Networks

Ines Chami, Rex Ying, Christopher Ré +1

Graph convolutional neural networks (GCNs) embed nodes in a graph into Euclidean space, which has been shown to incur a large distortion when embedding real-world graphs with scale…

cs.DS2020

From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering

Ines Chami, Albert Gu, Vaggos Chatziafratis +1

Similarity-based Hierarchical Clustering (HC) is a classical unsupervised machine learning algorithm that has traditionally been solved with heuristic algorithms like Average-Linka…

cs.LG2022

Machine Learning on Graphs: A Model and Comprehensive Taxonomy

Ines Chami, Sami Abu-El-Haija, Bryan Perozzi +2

There has been a surge of recent interest in learning representations for graph-structured data. Graph representation learning methods have generally fallen into three main categor…

cs.LG2021

HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections

Ines Chami, Albert Gu, Dat Nguyen +1

This paper studies Principal Component Analysis (PCA) for data lying in hyperbolic spaces. Given directions, PCA relies on: (1) a parameterization of subspaces spanned by these dir…

cs.CL2022

Ask Me Anything: A simple strategy for prompting language models

Simran Arora, Avanika Narayan, Mayee F. Chen +6

Large language models (LLMs) transfer well to new tasks out-of-the-box simply given a natural language prompt that demonstrates how to perform the task and no additional training.…

cs.CV2018

Referring Relationships

Ranjay Krishna, Ines Chami, Michael Bernstein +1

Images are not simply sets of objects: each image represents a web of interconnected relationships. These relationships between entities carry semantic meaning and help a viewer di…

cs.LG2020

Low-Dimensional Hyperbolic Knowledge Graph Embeddings

Ines Chami, Adva Wolf, Da-Cheng Juan +3

Knowledge graph (KG) embeddings learn low-dimensional representations of entities and relations to predict missing facts. KGs often exhibit hierarchical and logical patterns which…

cs.LG2022

Can Foundation Models Wrangle Your Data?

Avanika Narayan, Ines Chami, Laurel Orr +2

Foundation Models (FMs) are models trained on large corpora of data that, at very large scale, can generalize to new tasks without any task-specific finetuning. As these models con…