BPBryan Perozzi

Bryan Perozzi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Bryan Perozzi has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Graph Reasoning with LLMs (GReaL)

    by Anton Tsitsulin, Bryan Perozzi, Bahare Fatemi, Jonathan J. Halcrow

    Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications. Large Language Models (LLMs) have demonstrated impressive capabilities by advancing state-of-the-art on many language-based benchmarks. Their ability to process and understand natural language open exciting possibilities in various domains. Despite the remarkable progress in automated reasoning with natural text, reasoning on graphs with LLMs remains an understudied problem that has recently gained more attention. This tutorial builds upon recent advances in expressing reasoning problems through the lens of tasks on graph data. The first part of the tutorial will provide an in-depth discussion of techniques for representing graphs as inputs to LLMs. The second, hands-on, portion will demonstrate these techniques in a practical setting. As a learning outcome of participating in the tutorial, participants will be able to analyze graphs either on free-tier Colab or their local machines with the help of LLMs.


  • Open Access

    HUGE: Huge Unsupervised Graph Embeddings with TPUs

    by Brandon A. Mayer, Anton Tsitsulin, Hendrik Fichtenberger, Jonathan Halcrow, Bryan Perozzi

    Graphs are a representation of structured data that captures the relationships between sets of objects. With the ubiquity of available network data, there is increasing industrial and academic need to quickly analyze graphs with billions of nodes and trillions of edges. A common first step for network understanding is Graph Embedding, the process of creating a continuous representation of nodes in a graph. A continuous representation is often more amenable, especially at scale, for solving downstream machine learning tasks such as classification, link prediction, and clustering. 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. We verify the embedding space quality on real and synthetic large-scale datasets.


  • Open Access

    Graph Neural Networks in TensorFlow

    by Bryan Perozzi, Sami Abu-El-Haija, Anton Tsitsulin

    Graphs are general data structures that can represent information from a variety of domains (social, biomedical, online transactions, and many more). Graph Neural Networks (GNNs) are quickly becoming the de-facto Machine Learning models for learning from Graph data and hereby infer missing information, such as, predicting labels of nodes or imputing missing edges. In this tutorial we'll cover essential applications of Graph Machine Learning using TensorFlow GNN1[12], a Python framework that extends TensorFlow [1] with Graph Neural Networks (GNNs): models that leverage graph-structured data. TF-GNN is motivated and informed by years of applying graph representation learning to practical problems at Google [2-8, 10, 11, 13-19, 22-29]. In particular, TF-GNN focuses on the representation of heterogeneous graph data and supports the explicit modeling of an arbitrary number of relationship (edge) types between an arbitrary number of entity (node) types. These relationships can be used in combination with other TensorFlow components, e.g., a TF-GNN model might connect representations from a language model to those of a vision model and fine-tune these features for a node classification task. Many teams at Google run TF-GNN models in production. We believe this to be a direct consequence of TF-GNN's multi-layered API which is designed for accessibility to developers (regardless of their prior experience with machine learning).


  • Open Access

    HyperFormer: Learning Expressive Sparse Feature Representations via Hypergraph Transformer

    by Kaize Ding, Albert Jiongqian Liang, Bryan Perozzi, Ting Chen, Ruoxi Wang, Lichan Hong, Ed H. Chi, Huan Liu, Derek Zhiyuan Cheng

    Learning expressive representations for high-dimensional yet sparse features has been a longstanding problem in information retrieval. Though recent deep learning methods can partially solve the problem, they often fail to handle the numerous sparse features, particularly those tail feature values with infrequent occurrences in the training data. Worse still, existing methods cannot explicitly leverage the correlations among different instances to help further improve the representation learning on sparse features since such relational prior knowledge is not provided. To address these challenges, in this paper, we tackle the problem of representation learning on feature-sparse data from a graph learning perspective. Specifically, we propose to model the sparse features of different instances using hypergraphs where each node represents a data instance and each hyperedge denotes a distinct feature value. By passing messages on the constructed hypergraphs based on our Hypergraph Transformer (HyperFormer), the learned feature representations capture not only the correlations among different instances but also the correlations among features. Our experiments demonstrate that the proposed approach can effectively improve feature representation learning on sparse features.


  • Social Relation Inference via Label Propagation

    by Yingtao Tian, Haochen Chen, Bryan Perozzi, Muhao Chen, Xiaofei Sun, Steven Skiena


  • Open Access

    Enhanced Network Embeddings via Exploiting Edge Labels

    by 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. While achieving competitive performance on a variety of network inference tasks such as node classification and link prediction, these methods treat the relations between nodes as a binary variable and ignore the rich semantics of edges. In this work, we attempt to learn network embeddings which simultaneously preserve network structure and relations between nodes. Experiments on several real-world networks illustrate that by considering different relations between different node pairs, our method is capable of producing node embeddings of higher quality than a number of state-of-the-art network embedding methods, as evaluated on a challenging multi-label node classification task.