A survey on dynamic network embedding
Y Xie, C Li, B Yu, C Zhang, Z Tang - arXiv preprint arXiv:2006.08093, 2020 - arxiv.org
Real-world networks are composed of diverse interacting and evolving entities, while most
of existing researches simply characterize them as particular static networks, without …
of existing researches simply characterize them as particular static networks, without …
Monet: Debiasing graph embeddings via the metadata-orthogonal training unit
J Palowitch, B Perozzi - arXiv preprint arXiv:1909.11793, 2019 - arxiv.org
Are Graph Neural Networks (GNNs) fair? In many real world graphs, the formation of edges
is related to certain node attributes (eg gender, community, reputation). In this case …
is related to certain node attributes (eg gender, community, reputation). In this case …
Debiasing graph representations via metadata-orthogonal training
J Palowitch, B Perozzi - … in Social Networks Analysis and Mining …, 2020 - ieeexplore.ieee.org
In real world graphs, the formation of edges can be associated with certain sensitive features
of the nodes (eg gender, community, reputation). In this paper we argue that when such …
of the nodes (eg gender, community, reputation). In this paper we argue that when such …
Spine: Structural identity preserved inductive network embedding
Recent advances in the field of network embedding have shown that low-dimensional
network representation is playing a critical role in network analysis. Most existing network …
network representation is playing a critical role in network analysis. Most existing network …
Node pair information preserving network embedding based on adversarial networks
Network embedding aims to learn the low-dimensional node representations for networks,
which has attracted an increasing amount of attention in recent years. Most existing efforts in …
which has attracted an increasing amount of attention in recent years. Most existing efforts in …
Content to node: Self-translation network embedding
This paper concerns the problem of network embedding (NE), which aims to learn low-
dimensional representations for network nodes. Such dense representations offer great …
dimensional representations for network nodes. Such dense representations offer great …
FB2vec: A Novel Representation Learning Model for Forwarding Behaviors on Online Social Networks
L Ma, M Liao, X Gao, G Zhang, Q Yan… - Joint European Conference …, 2020 - Springer
Abstract Representation learning in online social networks has been an important research
task for better service, which targets at learning the low-dimensional vector representation …
task for better service, which targets at learning the low-dimensional vector representation …