no code implementations • 8 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)?
no code implementations • 8 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.
1 code implementation • 21 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.
no code implementations • 26 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.
1 code implementation • 17 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.
no code implementations • 26 May 2023 • Anton Tsitsulin, Marina Munkhoeva, Bryan Perozzi
Unsupervised learning has recently significantly gained in popularity, especially with deep learning-based approaches.
no code implementations • 18 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.
1 code implementation • 14 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.
1 code implementation • 7 Jul 2022 • Oleksandr Ferludin, Arno Eigenwillig, Martin Blais, Dustin Zelle, Jan Pfeifer, Alvaro Sanchez-Gonzalez, Wai Lok Sibon Li, Sami Abu-El-Haija, Peter Battaglia, Neslihan Bulut, Jonathan Halcrow, Filipe Miguel Gonçalves de Almeida, Pedro Gonnet, Liangze Jiang, Parth Kothari, Silvio Lattanzi, André Linhares, Brandon Mayer, Vahab Mirrokni, John Palowitch, Mihir Paradkar, Jennifer She, Anton Tsitsulin, Kevin Villela, Lisa Wang, David Wong, Bryan Perozzi
TensorFlow-GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow.
1 code implementation • 20 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.
1 code implementation • 4 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.
1 code implementation • 28 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.
no code implementations • 10 Jun 2021 • Judith Hermanns, Anton Tsitsulin, Marina Munkhoeva, Alex Bronstein, Davide Mottin, Panagiotis Karras
In this paper, we transfer the shape-analysis concept of functional maps from the continuous to the discrete case, and treat the graph alignment problem as a special case of the problem of finding a mapping between functions on graphs.
no code implementations • 14 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.
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.
no code implementations • 8 Jun 2020 • Anton Tsitsulin, Marina Munkhoeva, Davide Mottin, Panagiotis Karras, Ivan Oseledets, Emmanuel Müller
Low-dimensional representations, or embeddings, of a graph's nodes facilitate several practical data science and data engineering tasks.
no code implementations • 3 Mar 2020 • Anton Tsitsulin, Marina Munkhoeva, Bryan Perozzi
Graph comparison is a fundamental operation in data mining and information retrieval.
2 code implementations • ICLR 2020 • Anton Tsitsulin, Marina Munkhoeva, Davide Mottin, Panagiotis Karras, Alex Bronstein, Ivan Oseledets, Emmanuel Müller
The ability to represent and compare machine learning models is crucial in order to quantify subtle model changes, evaluate generative models, and gather insights on neural network architectures.
no code implementations • 15 Nov 2018 • Anton Tsitsulin, Davide Mottin, Panagiotis Karras, Alex Bronstein, Emmanuel Müller
Representing a graph as a vector is a challenging task; ideally, the representation should be easily computable and conducive to efficient comparisons among graphs, tailored to the particular data and analytical task at hand.
1 code implementation • 27 May 2018 • Anton Tsitsulin, Davide Mottin, Panagiotis Karras, Alex Bronstein, Emmanuel Müller
However, it is a hard task in terms of the expressiveness of the employed similarity measure and the efficiency of its computation.
Social and Information Networks
2 code implementations • 13 Mar 2018 • Anton Tsitsulin, Davide Mottin, Panagiotis Karras, Emmanuel Müller
Embedding a web-scale information network into a low-dimensional vector space facilitates tasks such as link prediction, classification, and visualization.