Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Halcrow, Jonathan"'
Autor:
Fatemi, Bahare, Kazemi, Mehran, Tsitsulin, Anton, Malkan, Karishma, Yim, Jinyeong, Palowitch, John, Seo, Sungyong, Halcrow, Jonathan, Perozzi, Bryan
Large language models (LLMs) have showcased remarkable reasoning capabilities, yet they remain susceptible to errors, particularly in temporal reasoning tasks involving complex temporal logic. Existing research has explored LLM performance on tempora
Externí odkaz:
http://arxiv.org/abs/2406.09170
Autor:
Sanford, Clayton, Fatemi, Bahare, Hall, Ethan, Tsitsulin, Anton, Kazemi, Mehran, Halcrow, Jonathan, Perozzi, Bryan, Mirrokni, Vahab
Which transformer scaling regimes are able to perfectly solve different classes of algorithmic problems? While tremendous empirical advances have been attained by transformer-based neural networks, a theoretical understanding of their algorithmic rea
Externí odkaz:
http://arxiv.org/abs/2405.18512
Autor:
Perozzi, Bryan, Fatemi, Bahare, Zelle, Dustin, Tsitsulin, Anton, Kazemi, Mehran, Al-Rfou, Rami, Halcrow, Jonathan
How can we best encode structured data into sequential form for use in large language models (LLMs)? In this work, we introduce a parameter-efficient method to explicitly represent structured data for LLMs. Our method, GraphToken, learns an encoding
Externí odkaz:
http://arxiv.org/abs/2402.05862
Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications such as social networks, recommender systems, and computational finance. Reasoning on graphs is essential for drawing inferences about the rela
Externí odkaz:
http://arxiv.org/abs/2310.04560
Autor:
Fatemi, Bahare, Abu-El-Haija, Sami, Tsitsulin, Anton, Kazemi, Mehran, Zelle, Dustin, Bulut, Neslihan, Halcrow, Jonathan, Perozzi, Bryan
Graph neural networks (GNNs) demonstrate outstanding performance in a broad range of applications. While the majority of GNN applications assume that a graph structure is given, some recent methods substantially expanded the applicability of GNNs by
Externí odkaz:
http://arxiv.org/abs/2308.10737
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
Externí odkaz:
http://arxiv.org/abs/2307.14490
Autor:
Carey, CJ, Halcrow, Jonathan, Jayaram, Rajesh, Mirrokni, Vahab, Schudy, Warren, Zhong, Peilin
A fundamental procedure in the analysis of massive datasets is the construction of similarity graphs. Such graphs play a key role for many downstream tasks, including clustering, classification, graph learning, and nearest neighbor search. For these
Externí odkaz:
http://arxiv.org/abs/2212.02635
Autor:
Ferludin, Oleksandr, Eigenwillig, Arno, Blais, Martin, Zelle, Dustin, Pfeifer, Jan, Sanchez-Gonzalez, Alvaro, Li, Wai Lok Sibon, Abu-El-Haija, Sami, Battaglia, Peter, Bulut, Neslihan, Halcrow, Jonathan, de Almeida, Filipe Miguel Gonçalves, Gonnet, Pedro, Jiang, Liangze, Kothari, Parth, Lattanzi, Silvio, Linhares, André, Mayer, Brandon, Mirrokni, Vahab, Palowitch, John, Paradkar, Mihir, She, Jennifer, Tsitsulin, Anton, Villela, Kevin, Wang, Lisa, Wong, David, Perozzi, Bryan
TensorFlow-GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow. It is designed from the bottom up to support the kinds of rich heterogeneous graph data that occurs in today's information ecosystems. In addition to enabling mach
Externí odkaz:
http://arxiv.org/abs/2207.03522
Autor:
Halcrow, Jonathan
The study of turbulence has been dominated historically by a bottom-up approach, with a much stronger emphasis on the physical structure of flows than on that of the dynam- ical state space. Turbulence has traditionally been described in terms of va
Externí odkaz:
http://hdl.handle.net/1853/24724
How can we find the right graph for semi-supervised learning? In real world applications, the choice of which edges to use for computation is the first step in any graph learning process. Interestingly, there are often many types of similarity availa
Externí odkaz:
http://arxiv.org/abs/2007.12002