Search Results for author: Bryan Perozzi

Found 50 papers, 30 papers with code

Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank

1 code implementation14 Jul 2022 Alessandro Epasto, Vahab Mirrokni, Bryan Perozzi, Anton Tsitsulin, Peilin Zhong

Personalized PageRank (PPR) is a fundamental tool in unsupervised learning of graph representations such as node ranking, labeling, and graph embedding.

Graph Embedding Graph Learning +1

Synthetic Graph Generation to Benchmark Graph Learning

1 code implementation4 Apr 2022 Anton Tsitsulin, Benedek Rozemberczki, John Palowitch, Bryan Perozzi

This shockingly small sample size (~10) allows for only limited scientific insight into the problem.

Graph Generation Graph Learning +2

Tackling Provably Hard Representative Selection via Graph Neural Networks

1 code implementation20 May 2022 Mehran Kazemi, Anton Tsitsulin, Hossein Esfandiari, Mohammadhossein Bateni, Deepak Ramachandran, Bryan Perozzi, Vahab Mirrokni

Representative Selection (RS) is the problem of finding a small subset of exemplars from a dataset that is representative of the dataset.

Active Learning Data Compression +1

UGSL: A Unified Framework for Benchmarking Graph Structure Learning

1 code implementation21 Aug 2023 Bahare Fatemi, Sami Abu-El-Haija, Anton Tsitsulin, Mehran Kazemi, Dustin Zelle, Neslihan Bulut, Jonathan Halcrow, Bryan Perozzi

We implement a wide range of existing models in our framework and conduct extensive analyses of the effectiveness of different components in the framework.

Benchmarking Graph structure learning

DDGK: Learning Graph Representations for Deep Divergence Graph Kernels

1 code implementation21 Apr 2019 Rami Al-Rfou, Dustin Zelle, Bryan Perozzi

Second, for each pair of graphs, we train a cross-graph attention network which uses the node representations of an anchor graph to reconstruct another graph.

Feature Engineering Graph Attention +2

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

2 code implementations6 May 2019 Alessandro Epasto, Bryan Perozzi

Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph.

Graph Embedding Link Prediction

DeepWalk: Online Learning of Social Representations

14 code implementations26 Mar 2014 Bryan Perozzi, Rami Al-Rfou, Steven Skiena

We present DeepWalk, a novel approach for learning latent representations of vertices in a network.

Anomaly Detection Language Modelling +1

Don't Walk, Skip! Online Learning of Multi-scale Network Embeddings

2 code implementations6 May 2016 Bryan Perozzi, Vivek Kulkarni, Haochen Chen, Steven Skiena

We present Walklets, a novel approach for learning multiscale representations of vertices in a network.

Social and Information Networks Physics and Society

Watch Your Step: Learning Node Embeddings via Graph Attention

2 code implementations NeurIPS 2018 Sami Abu-El-Haija, Bryan Perozzi, Rami Al-Rfou, Alex Alemi

Graph embedding methods represent nodes in a continuous vector space, preserving information from the graph (e. g. by sampling random walks).

Graph Attention Graph Embedding +2

Splitter: Learning Node Representations that Capture Multiple Social Contexts

1 code implementation WWW 2019 Alessandro Epasto, Bryan Perozzi

Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph.

Graph Embedding Link Prediction +1

Machine Learning on Graphs: A Model and Comprehensive Taxonomy

1 code implementation7 May 2020 Ines Chami, Sami Abu-El-Haija, Bryan Perozzi, Christopher Ré, Kevin Murphy

The second, graph regularized neural networks, leverages graphs to augment neural network losses with a regularization objective for semi-supervised learning.

BIG-bench Machine Learning Graph Attention +3

GraphWorld: Fake Graphs Bring Real Insights for GNNs

1 code implementation28 Feb 2022 John Palowitch, Anton Tsitsulin, Brandon Mayer, Bryan Perozzi

Using GraphWorld, a user has fine-grained control over graph generator parameters, and can benchmark arbitrary GNN models with built-in hyperparameter tuning.

Benchmarking

Examining the Effects of Degree Distribution and Homophily in Graph Learning Models

1 code implementation17 Jul 2023 Mustafa Yasir, John Palowitch, Anton Tsitsulin, Long Tran-Thanh, Bryan Perozzi

In this work we examine how two additional synthetic graph generators can improve GraphWorld's evaluation; LFR, a well-established model in the graph clustering literature and CABAM, a recent adaptation of the Barabasi-Albert model tailored for GNN benchmarking.

Benchmarking Graph Clustering +3

N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification

1 code implementation24 Feb 2018 Sami Abu-El-Haija, Amol Kapoor, Bryan Perozzi, Joonseok Lee

Graph Convolutional Networks (GCNs) have shown significant improvements in semi-supervised learning on graph-structured data.

General Classification Node Classification

TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs

1 code implementation NeurIPS 2023 Phitchaya Mangpo Phothilimthana, Sami Abu-El-Haija, Kaidi Cao, Bahare Fatemi, Mike Burrows, Charith Mendis, Bryan Perozzi

TpuGraphs provides 25x more graphs than the largest graph property prediction dataset (with comparable graph sizes), and 770x larger graphs on average compared to existing performance prediction datasets on machine learning programs.

Graph Property Prediction Property Prediction

HARP: Hierarchical Representation Learning for Networks

3 code implementations23 Jun 2017 Haochen Chen, Bryan Perozzi, Yifan Hu, Steven Skiena

We present HARP, a novel method for learning low dimensional embeddings of a graph's nodes which preserves higher-order structural features.

Social and Information Networks

Pathfinder Discovery Networks for Neural Message Passing

1 code implementation24 Oct 2020 Benedek Rozemberczki, Peter Englert, Amol Kapoor, Martin Blais, Bryan Perozzi

Additional results from a challenging suite of node classification experiments show how PDNs can learn a wider class of functions than existing baselines.

Graph Attention Node Classification +1

Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data

1 code implementation NeurIPS 2021 Qi Zhu, Natalia Ponomareva, Jiawei Han, Bryan Perozzi

In this work we present a method, Shift-Robust GNN (SR-GNN), designed to account for distributional differences between biased training data and the graph's true inference distribution.

Learning Edge Representations via Low-Rank Asymmetric Projections

1 code implementation16 May 2017 Sami Abu-El-Haija, Bryan Perozzi, Rami Al-Rfou

Individually, both of these contributions improve the learned representations, especially when there are memory constraints on the total size of the embeddings.

Link Prediction

Learning Large Graph Property Prediction via Graph Segment Training

1 code implementation NeurIPS 2023 Kaidi Cao, Phitchaya Mangpo Phothilimthana, Sami Abu-El-Haija, Dustin Zelle, Yanqi Zhou, Charith Mendis, Jure Leskovec, Bryan Perozzi

Here we propose Graph Segment Training (GST), a general framework that utilizes a divide-and-conquer approach to allow learning large graph property prediction with a constant memory footprint.

Graph Property Prediction Property Prediction

Graph Generative Model for Benchmarking Graph Neural Networks

1 code implementation10 Jul 2022 Minji Yoon, Yue Wu, John Palowitch, Bryan Perozzi, Ruslan Salakhutdinov

As the field of Graph Neural Networks (GNN) continues to grow, it experiences a corresponding increase in the need for large, real-world datasets to train and test new GNN models on challenging, realistic problems.

Benchmarking Graph Generation +1

Enhanced Network Embeddings via Exploiting Edge Labels

1 code implementation13 Sep 2018 Haochen Chen, Xiaofei Sun, Yingtao Tian, Bryan Perozzi, Muhao Chen, Steven Skiena

Network embedding methods aim at learning low-dimensional latent representation of nodes in a network.

Social and Information Networks Physics and Society

Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks

1 code implementation6 Jul 2020 Amol Kapoor, Xue Ben, Luyang Liu, Bryan Perozzi, Matt Barnes, Martin Blais, Shawn O'Banion

In this work, we examine a novel forecasting approach for COVID-19 case prediction that uses Graph Neural Networks and mobility data.

Time Series Time Series Forecasting

Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning

1 code implementation ICLR 2021 Elan Markowitz, Keshav Balasubramanian, Mehrnoosh Mirtaheri, Sami Abu-El-Haija, Bryan Perozzi, Greg Ver Steeg, Aram Galstyan

We propose Graph Traversal via Tensor Functionals(GTTF), a unifying meta-algorithm framework for easing the implementation of diverse graph algorithms and enabling transparent and efficient scaling to large graphs.

Graph Representation Learning

Freshman or Fresher? Quantifying the Geographic Variation of Internet Language

2 code implementations22 Oct 2015 Vivek Kulkarni, Bryan Perozzi, Steven Skiena

Our analysis of British and American English over a period of 100 years reveals that semantic variation between these dialects is shrinking.

A Tutorial on Network Embeddings

2 code implementations8 Aug 2018 Haochen Chen, Bryan Perozzi, Rami Al-Rfou, Steven Skiena

We further demonstrate the applications of network embeddings, and conclude the survey with future work in this area.

Social and Information Networks

Zero-shot Transfer Learning within a Heterogeneous Graph via Knowledge Transfer Networks

1 code implementation3 Mar 2022 Minji Yoon, John Palowitch, Dustin Zelle, Ziniu Hu, Ruslan Salakhutdinov, Bryan Perozzi

We propose a zero-shot transfer learning module for HGNNs called a Knowledge Transfer Network (KTN) that transfers knowledge from label-abundant node types to zero-labeled node types through rich relational information given in the HG.

Domain Adaptation Graph Learning +2

On the Convergent Properties of Word Embedding Methods

no code implementations12 May 2016 Yingtao Tian, Vivek Kulkarni, Bryan Perozzi, Steven Skiena

Do word embeddings converge to learn similar things over different initializations?

Word Embeddings

Statistically Significant Detection of Linguistic Change

no code implementations12 Nov 2014 Vivek Kulkarni, Rami Al-Rfou, Bryan Perozzi, Steven Skiena

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

Change Point Detection Time Series +1

POLYGLOT-NER: Massive Multilingual Named Entity Recognition

no code implementations14 Oct 2014 Rami Al-Rfou, Vivek Kulkarni, Bryan Perozzi, Steven Skiena

We describe a system that builds Named Entity Recognition (NER) annotators for 40 major languages using Wikipedia and Freebase.

Information Retrieval Machine Translation +7

Inducing Language Networks from Continuous Space Word Representations

no code implementations6 Mar 2014 Bryan Perozzi, Rami Al-Rfou, Vivek Kulkarni, Steven Skiena

Recent advancements in unsupervised feature learning have developed powerful latent representations of words.

Polyglot: Distributed Word Representations for Multilingual NLP

no code implementations WS 2013 Rami Al-Rfou, Bryan Perozzi, Steven Skiena

We quantitatively demonstrate the utility of our word embeddings by using them as the sole features for training a part of speech tagger for a subset of these languages.

Language Modelling Multilingual NLP +1

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

no code implementations5 Apr 2014 Vivek Kulkarni, Rami Al-Rfou', Bryan Perozzi, Steven Skiena

We evaluate the performance of training the model on the GPU and present optimizations that boost the performance on the GPU. One of the key optimizations, we propose increases the performance of a function involved in calculating and updating the gradient by approximately 50 times on the GPU for sufficiently large batch sizes.

The Expressive Power of Word Embeddings

no code implementations15 Jan 2013 Yanqing Chen, Bryan Perozzi, Rami Al-Rfou, Steven Skiena

We seek to better understand the difference in quality of the several publicly released embeddings.

Benchmarking Sentence +1

Network of Graph Convolutional Networks Trained on Random Walks

no code implementations ICLR 2018 Sami Abu-El-Haija, Amol Kapoor, Bryan Perozzi, Joonseok Lee

Graph Convolutional Networks (GCNs) are a recently proposed architecture which has had success in semi-supervised learning on graph-structured data.

General Classification Node Classification

MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit

no code implementations25 Sep 2019 John Palowitch, Bryan Perozzi

In this paper, we show that when metadata is correlated with the formation of node neighborhoods, unsupervised node embedding dimensions learn this metadata.

Recommendation Systems

Graph Clustering with Graph Neural Networks

no code implementations NeurIPS 2023 Anton Tsitsulin, John Palowitch, Bryan Perozzi, Emmanuel Müller

Graph Neural Networks (GNNs) have achieved state-of-the-art results on many graph analysis tasks such as node classification and link prediction.

Attribute Clustering +3

Grale: Designing Networks for Graph Learning

no code implementations23 Jul 2020 Jonathan Halcrow, Alexandru Moşoi, Sam Ruth, Bryan Perozzi

Interestingly, there are often many types of similarity available to choose as the edges between nodes, and the choice of edges can drastically affect the performance of downstream semi-supervised learning systems.

Graph Learning

InstantEmbedding: Efficient Local Node Representations

no code implementations14 Oct 2020 Ştefan Postăvaru, Anton Tsitsulin, Filipe Miguel Gonçalves de Almeida, Yingtao Tian, Silvio Lattanzi, Bryan Perozzi

In this paper, we introduce InstantEmbedding, an efficient method for generating single-node representations using local PageRank computations.

Link Prediction Node Classification +1

On Classification Thresholds for Graph Attention with Edge Features

no code implementations18 Oct 2022 Kimon Fountoulakis, Dake He, Silvio Lattanzi, Bryan Perozzi, Anton Tsitsulin, Shenghao Yang

In CSBM the nodes and edge features are obtained from a mixture of Gaussians and the edges from a stochastic block model.

Classification Graph Attention +2

Unsupervised Embedding Quality Evaluation

no code implementations26 May 2023 Anton Tsitsulin, Marina Munkhoeva, Bryan Perozzi

Unsupervised learning has recently significantly gained in popularity, especially with deep learning-based approaches.

Self-Supervised Learning

HUGE: Huge Unsupervised Graph Embeddings with TPUs

no code implementations26 Jul 2023 Brandon Mayer, Anton Tsitsulin, Hendrik Fichtenberger, Jonathan Halcrow, Bryan Perozzi

A high-performance graph embedding architecture leveraging Tensor Processing Units (TPUs) with configurable amounts of high-bandwidth memory is presented that simplifies the graph embedding problem and can scale to graphs with billions of nodes and trillions of edges.

Graph Embedding Link Prediction

Talk like a Graph: Encoding Graphs for Large Language Models

no code implementations6 Oct 2023 Bahare Fatemi, Jonathan Halcrow, Bryan Perozzi

Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications such as social networks, recommender systems, and computational finance.

Recommendation Systems

The Graph Lottery Ticket Hypothesis: Finding Sparse, Informative Graph Structure

no code implementations8 Dec 2023 Anton Tsitsulin, Bryan Perozzi

Subsequently, we define the notion of a "winning ticket" for graph structure - an extremely sparse subset of edges that can deliver a robust approximation of the entire graph's performance.

Graph Learning

Let Your Graph Do the Talking: Encoding Structured Data for LLMs

no code implementations8 Feb 2024 Bryan Perozzi, Bahare Fatemi, Dustin Zelle, Anton Tsitsulin, Mehran Kazemi, Rami Al-Rfou, Jonathan Halcrow

How can we best encode structured data into sequential form for use in large language models (LLMs)?

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