node2vec: Scalable feature learning for networks
A Grover, J Leskovec - Proceedings of the 22nd ACM SIGKDD …, 2016 - dl.acm.org
Prediction tasks over nodes and edges in networks require careful effort in engineering
features used by learning algorithms. Recent research in the broader field of representation …
features used by learning algorithms. Recent research in the broader field of representation …
Towards robust graph neural networks for noisy graphs with sparse labels
Graph Neural Networks (GNNs) have shown their great ability in modeling graph structured
data. However, real-world graphs usually contain structure noises and have limited labeled …
data. However, real-world graphs usually contain structure noises and have limited labeled …
Deepwalk: Online learning of social representations
We present DeepWalk, a novel approach for learning latent representations of vertices in a
network. These latent representations encode social relations in a continuous vector space …
network. These latent representations encode social relations in a continuous vector space …
Rolx: structural role extraction & mining in large graphs
K Henderson, B Gallagher, T Eliassi-Rad… - Proceedings of the 18th …, 2012 - dl.acm.org
Given a network, intuitively two nodes belong to the same role if they have similar structural
behavior. Roles should be automatically determined from the data, and could be, for …
behavior. Roles should be automatically determined from the data, and could be, for …
It's who you know: graph mining using recursive structural features
Given a graph, how can we extract good features for the nodes? For example, given two
large graphs from the same domain, how can we use information in one to do classification …
large graphs from the same domain, how can we use information in one to do classification …
[PDF][PDF] Discriminative deep random walk for network classification
J Li, J Zhu, B Zhang - Proceedings of the 54th Annual Meeting of …, 2016 - aclanthology.org
Abstract Deep Random Walk (DeepWalk) can learn a latent space representation for
describing the topological structure of a network. However, for relational network …
describing the topological structure of a network. However, for relational network …
Causal network motifs: Identifying heterogeneous spillover effects in a/b tests
Randomized experiments, or “A/B” tests, remain the gold standard for evaluating the causal
effect of a policy intervention or product change. However, experimental settings, such as …
effect of a policy intervention or product change. However, experimental settings, such as …
Microblog sentiment analysis via embedding social contexts into an attentive LSTM
J Yang, X Zou, W Zhang, H Han - Engineering Applications of Artificial …, 2021 - Elsevier
With the rise of microblogging services like Twitter and Sina Weibo, users are able to post
various contents on breaking news, public events, or products conveniently and swiftly …
various contents on breaking news, public events, or products conveniently and swiftly …
[PDF][PDF] Cautious Collective Classification.
LK McDowell, KM Gupta, DW Aha - Journal of Machine Learning Research, 2009 - jmlr.org
Many collective classification (CC) algorithms have been shown to increase accuracy when
instances are interrelated. However, CC algorithms must be carefully applied because their …
instances are interrelated. However, CC algorithms must be carefully applied because their …
[HTML][HTML] Exploiting causality in gene network reconstruction based on graph embedding
Gene network reconstruction is a bioinformatics task that aims at modelling the complex
regulatory activities that may occur among genes. This task is typically solved by means of …
regulatory activities that may occur among genes. This task is typically solved by means of …