Network Representation Learning: Consolidation and Renewed Bearing

Gurukar, Saket; Vijayan, Priyesh; Srinivasan, Aakash; Bajaj, Goonmeet; Keymanesh, Moniba; Kumar, Saravana; Maneriker, Pranav; Mitra, Anasua; Patel, Vedang; Ravindran, Balaraman; Parthasarathy, Srinivasan

doi:10.48550/arxiv.1905.00987

Cited by 4 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Link predictions models are trained using 20 randomized train-test splits. Following prior works [9] for link prediction tasks, we split the dataset into training and test data using the following procedure. We first randomly sample 20%…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

FairMod: Fair Link Prediction and Recommendation via Graph Modification

Current¹,

He²,

Gurukar³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

As machine learning becomes more widely adopted across domains, it is critical that researchers and ML engineers think about the inherent biases in the data that may be perpetuated by the model. Recently, many studies have shown that such biases are also imbibed in Graph Neural Network (GNN) models if the input graph is biased. In this work, we aim to mitigate the bias learned by GNNs through modifying the input graph. To that end, we propose FairMod, a Fair Graph Modification methodology with three formulations: the Global Fairness Optimization (GFO), Community Fairness Optimization (CFO), and Fair Edge Weighting (FEW) models. Our proposed models perform either microscopic or macroscopic edits to the input graph while training GNNs and learn node embeddings that are both accurate and fair under the context of link recommendations. We demonstrate the effectiveness of our approach on four real world datasets and show that we can improve the recommendation fairness by several factors at negligible cost to link prediction accuracy.CCS Concepts: • Computing methodologies → Neural networks.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Quality: To evaluate embedding quality on the link prediction task, we use the AUROC and F1-Score metrics following the procedures described in [9]. We train a logistic regression model as a classifier for positive/negative edges using an equal number of positive and negative edges randomly selected from the training set.…”

Section: Metricsmentioning

confidence: 99%

FairMod: Fair Link Prediction and Recommendation via Graph Modification

Current¹,

He²,

Gurukar³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The Adam Optimizer is used for model training. Evaluation Metrics: We evaluate the quality of the embeddings through multi-label node classification (Perozzi, Al-Rfou, and Skiena 2014;Grover and Leskovec 2016) and link prediction (Gurukar, Vijayan et al 2019). Specifically, for node classification, we run a 10-fold cross validation using the embeddings as features and report the average Micro-F1 and average Macro-F1.…”

Section: Experiments and Analysismentioning

confidence: 99%

MILE: A Multi-Level Framework for Scalable Graph Embedding

Liang

Gurukar

Parthasarathy

2021

ICWSM

View full text Add to dashboard Cite

Recently there has been a surge of interest in designing graph embedding methods. Few, if any, can scale to a large-sized graph with millions of nodes due to both computational complexity and memory requirements. In this paper, we relax this limitation by introducing the MultI-Level Embedding (MILE) framework – a generic methodology allowing contemporary graph embedding methods to scale to large graphs. MILE repeatedly coarsens the graph into smaller ones using a hybrid matching technique to maintain the backbone structure of the graph. It then applies existing embedding methods on the coarsest graph and refines the embeddings to the original graph through a graph convolution neural network that it learns. The proposed MILE framework is agnostic to the underlying graph embedding techniques and can be applied to many existing graph embedding methods without modifying them. We employ our framework on several popular graph embedding techniques and conduct embedding for real-world graphs. Experimental results on five large-scale datasets demonstrate that MILE significantly boosts the speed (order of magnitude) of graph embedding while generating embeddings of better quality, for the task of node classification. MILE can comfortably scale to a graph with 9 million nodes and 40 million edges, on which existing methods run out of memory or take too long to compute on a modern workstation. Our code and data are publicly available with detailed instructions for adding new base embedding methods: https://github.com/jiongqian/MILE.

show abstract

“…As an effort of generalizing convolution neural network to the graphs and manifolds, graph neural networks is proposed to analyze graph-structured data. They have achieved state-of-the-art performance in node classification (Kipf & Welling, 2016), knowledge graph completion (Schlichtkrull et al, 2018), link prediction (Dettmers et al, 2018;Gurukar et al, 2019), combinatorial optimization (Li et al, 2018b;Khalil et al, 2017), property prediction (Duvenaud et al, 2015;Xie & Grossman, 2018) and physics simulation (Sanchez-Gonzalez et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

Graph Coarsening with Neural Networks

Cai,

Wang,

Wang

2021

Preprint

Self Cite

View full text Add to dashboard Cite

As large-scale graphs become increasingly more prevalent, it poses significant computational challenges to process, extract and analyze large graph data. Graph coarsening is one popular technique to reduce the size of a graph while maintaining essential properties. Despite rich graph coarsening literature, there is only limited exploration of data-driven methods in the field. In this work, we leverage the recent progress of deep learning on graphs for graph coarsening. We first propose a framework for measuring the quality of coarsening algorithm and show that depending on the goal, we need to carefully choose the Laplace operator on the coarse graph and associated projection/lift operators. Motivated by the observation that the current choice of edge weight for the coarse graph may be suboptimal, we parametrize the weight assignment map with graph neural networks and train it to improve the coarsening quality in an unsupervised way. Through extensive experiments on both synthetic and real networks, we demonstrate that our method significantly improves common graph coarsening methods under various metrics, reduction ratios, graph sizes, and graph types. It generalizes to graphs of larger size (25× of training graphs), is adaptive to different losses (differentiable and non-differentiable), and scales to much larger graphs than previous work.

show abstract

Network Representation Learning: Consolidation and Renewed Bearing

Cited by 4 publications

References 0 publications

FairMod: Fair Link Prediction and Recommendation via Graph Modification

FairMod: Fair Link Prediction and Recommendation via Graph Modification

MILE: A Multi-Level Framework for Scalable Graph Embedding

Graph Coarsening with Neural Networks

Contact Info

Product

Resources

About