Distributed GraphLab: A Framework for Machine Learning in the Cloud

By Yucheng Low, Joseph E. Gonzalez, Aapo Kyrola, Danny Bickson, Carlos Guestrin, Joseph M Hellerstein. 2012

687 citations recorded by the source corpus.

Subfields: Graph Learning, ML Systems & Hardware

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Graph Learning

1. Quoc V. Le
2. Gerben de Vries
3. S. D. de Rooij
4. Peter Sanders
5. Henning Meyerhenke
6. Aydin Buluç
7. Ilya Safro
8. Andrew Y. Ng

In ML Systems & Hardware

1. Quoc V. Le
2. Andrew W. Senior
3. Phillip B. Gibbons
4. Rajat Monga
5. G. R. Ganger
6. Odej Kao
7. Berthold Reinwald
8. Vivek Seshadri

Citations in the corpus

• The Non-IID Data Quagmire of Decentralized Machine Learning (2019, background): “There are many large-scale ML systems that aim to enable efficient ML training with centralized datasets (e.g., (Recht et al., 2011; Low et al., 2012; Chilimbi et al., 2014; Dean et al., 2012; Ho et al., 2013; Cui et al., 2014; Li et al., 2014a; Chen et al., 2015; Goyal et al., 2017)), where the…”
• Quantitative missense variant effect prediction using large-scale mutagenesis data (2017, neutral): “…and Algorithms Python/2.7.3 Python https://www.python.org/ Numpy/1.13.1 van der Walt et al. (2011) http://www.numpy.org/ GraphLab/2.1 Low et al. (2012) https://turi.com/ Scipy/0.19.1 Jones et al. (2001) https://www.scipy.org/ scikit-learn/0.17.0 Pedregosa et al. (2011)…”
• Substructure counting graph kernels for machine learning from RDF data (2015, methodology): “However, the kernels discussed in this framework, and especially the kernels computed directly on the RDF graph, are suitable to implement on large graph processing platforms, such as GraphLab [39] and Pregel [40].”
• PipeDream: Fast and Efficient Pipeline Parallel DNN Training (2018, background): “For machine learning (ML) problems such as matrix factorization, topic modeling, and linear regression, prior work [29, 27, 45, 23] has shown that model parallelism can often achieve faster training times than data parallelism because of the improved statistical efficiency that arises from not using…”
• Processing Data Where It Makes Sense: Enabling In-Memory Computation (2019, background): “A popular modern application is large-scale graph processing [87, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193].”
• SystemML: Declarative Machine Learning on Spark (2016, methodology): “Furthermore, graph processing systems like GraphLab [23] often provide vertex-centric abstractions for graph-parallel operations.”