most citedMixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

270 citations · 484 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2019270 cited

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor +5

Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mix…

cs.SI2019109 cited

Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts

Alessandro Epasto, Bryan Perozzi

Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph. But can nodes really be best described by a single vector rep…

cs.LG201958 cited

DDGK: Learning Graph Representations for Deep Divergence Graph Kernels

Rami Al-Rfou, Dustin Zelle, Bryan Perozzi

Can neural networks learn to compare graphs without feature engineering? In this paper, we show that it is possible to learn representations for graph similarity with neither domai…

cs.CL20149 cited

Statistically Significant Detection of Linguistic Change

Vivek Kulkarni, Rami Al-Rfou, Bryan Perozzi +1

We propose a new computational approach for tracking and detecting statistically significant linguistic shifts in the meaning and usage of words. Such linguistic shifts are especia…

cs.CL201438 cited

POLYGLOT-NER: Massive Multilingual Named Entity Recognition

Rami Al-Rfou, Vivek Kulkarni, Bryan Perozzi +1

The increasing diversity of languages used on the web introduces a new level of complexity to Information Retrieval (IR) systems. We can no longer assume that textual content is wr…

cs.LG2014

Exploring the power of GPU's for training Polyglot language models

Vivek Kulkarni, Rami Al-Rfou', Bryan Perozzi +1

One of the major research trends currently is the evolution of heterogeneous parallel computing. GP-GPU computing is being widely used and several applications have been designed t…