Fast Random Walk with Restart and Its Applications

By Hanghang Tong, Christos Faloutsos, Jia-Yu Pan. 2006

1,307 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time (2017, methodology): “The basic random walk procedure BasicRandomWalk is described in Algorithm 1 [28].”
Supervised random walks: predicting and recommending links in social networks (2010, methodology): “The idea is to design an algorithm that will assign higher scores to nodes which s created links to than to those that s did not link to. PageRank [25] and variants like Personalized PageRank [17, 15] and Random Walks with Restarts [ 31 ] are popular methods for ranking nodes on graphs.”
On social networks and collaborative recommendation (2009, methodology): “The authors of [18] propose fast approximations of the original RWR method ensuring up to 90% or better quality, which takes into account properties of social graphs, namely linear correlations and community-like structure.”
Modeling Relation Paths for Representation Learning of Knowledge Bases (2015, background): “Most of these works regard each relation and path as discrete symbols, and deal with them us-ing graph-based algorithms, such as random walks with restart (Tong et al., 2006).”
Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems (2019, methodology): “niformly sample F friends as 5 input data; 2) for friend number less than F, we pad zeros to obtain a F-dimensional vector. We also experiment other sample methods like random walk with restart (RWR) [28] on a sub-graph near central node, but we •nd that uniformly sampling over adjacent nodes can ac”
Exploiting Temporal Dynamics in Sybil Defenses (2015, methodology): “…between the trust seed and the Sybils and the average distance between the trust seed and the benign identities as our distance metric, where and the dist ( a, b ) represents the inverse of the aﬃnity be-tween a and b , and the aﬃnity is computed by random walk with restart method as in [25].”
Fast shortest path distance estimation in large networks (2009, neutral): “Approximation methods for computing other graph proximity functions that are based on random walks, such as personalized pagerank and random walk with restart, have also been studied recently [14, 33].”
You Are Who You Know and How You Behave: Attribute Inference Attacks via Users' Social Friends and Behaviors (2016, background): “Therefore, Phase 1 of VIAL can be viewed as performing a random walk with a restart [40] on the subgraph consisting of social nodes and social links, where the matrix MT and α are the transition matrix and restart probability of the random walk, respectively.”
Location recommendation for location-based social networks (2010, background): “Hence, scalability is a critical issue since large-scale matrix multiplication incurs tremendous computational overhead for collaborative recommendation [5, 6, 7].”
Joint Link Prediction and Attribute Inference Using a Social-Attribute Network (2014, methodology): “The attributes-to-weight mapping function can be learned using an approach similar to the one proposed by Backstrom and Leskovec [2011”
Ieee Transactions on Knowledge and Data Engineering, Manuscropt Id 1 Social Recommendation with Cross-domain Transferable Knowledge (neutral): “Tong et al. [39] proposed a computationally efficient random walk algorithm.”
A Survey of Link Prediction in Complex Networks (2016, methodology): “This model is known as a random walk with restart [Tong et al. 2006].”
Generative Image Segmentation Using Random Walks with Restart (2008, methodology): “In this case, some approximation methods such as Fast Random Walk with Restart method [16] can be used.”
HeteSim: A General Framework for Relevance Measure in Heterogeneous Networks (2013, background): “It is extended to the scalable calculation for online queries [13], [14] an d the topk answers [15].”
Recommender Systems (2012, methodology): “(44) A fast algorithm to calculate this index was proposed [153] and the application to recommender systems was studied in [120] where it was found that this similarity performs better than the Pearson correlation coefficient.”
Mining of Massive Datasets (2011, background): “More detail on relations and relational algebra can be found in [16].”