Adversarial attacks on node embeddings via graph poisoning
A Bojchevski, S Günnemann - International Conference on …, 2019 - proceedings.mlr.press
The goal of network representation learning is to learn low-dimensional node embeddings
that capture the graph structure and are useful for solving downstream tasks. However …
that capture the graph structure and are useful for solving downstream tasks. However …
Gelling, and melting, large graphs by edge manipulation
Controlling the dissemination of an entity (eg, meme, virus, etc) on a large graph is an
interesting problem in many disciplines. Examples include epidemiology, computer security …
interesting problem in many disciplines. Examples include epidemiology, computer security …
D2D big data: Content deliveries over wireless device-to-device sharing in large-scale mobile networks
Recently the topic of how to effectively offload cellular traffic onto device-to-device sharing
among users in proximity has been gaining more and more attention from global …
among users in proximity has been gaining more and more attention from global …
Gcomb: Learning budget-constrained combinatorial algorithms over billion-sized graphs
S Manchanda, A Mittal, A Dhawan… - Advances in …, 2020 - proceedings.neurips.cc
There has been an increased interest in discovering heuristics for combinatorial problems
on graphs through machine learning. While existing techniques have primarily focused on …
on graphs through machine learning. While existing techniques have primarily focused on …
Scalable attack on graph data by injecting vicious nodes
Recent studies have shown that graph convolution networks (GCNs) are vulnerable to
carefully designed attacks, which aim to cause misclassification of a specific node on the …
carefully designed attacks, which aim to cause misclassification of a specific node on the …
Holistic influence maximization: Combining scalability and efficiency with opinion-aware models
The steady growth of graph data from social networks has resulted in wide-spread research
in finding solutions to the influence maximization problem. In this paper, we propose a …
in finding solutions to the influence maximization problem. In this paper, we propose a …
Learning heuristics over large graphs via deep reinforcement learning
There has been an increased interest in discovering heuristics for combinatorial problems
on graphs through machine learning. While existing techniques have primarily focused on …
on graphs through machine learning. While existing techniques have primarily focused on …
On popularity prediction of videos shared in online social networks
Popularity prediction, with both technological and economic importance, has been
extensively studied for conventional video sharing sites (VSSes), where the videos are …
extensively studied for conventional video sharing sites (VSSes), where the videos are …
Who will retweet this? automatically identifying and engaging strangers on twitter to spread information
There has been much effort on studying how social media sites, such as Twitter, help
propagate information in different situations, including spreading alerts and SOS messages …
propagate information in different situations, including spreading alerts and SOS messages …
Friend recommendation with content spread enhancement in social networks
Social network is becoming an increasingly popular media for information sharing. More and
more people are interacting with others via major social network sites such as Twitter and …
more people are interacting with others via major social network sites such as Twitter and …