Structural Deep Network Embedding - SIGKDD

In order to address the structure-preserving and sparsity prob-lems in the deep model, we further propose to exploit the ﬁrst-order and second-order proximity [26] jointly into the learning process. The ﬁrst-order proximity is the local pairwise similarity only be-tween the vertexes linked by edges, which characterizes the local network ...

Network, Structural, Deep, Embedding, Preserving, Structural deep network embedding

Download Structural Deep Network Embedding - SIGKDD

Information

Domain:

Source:

Link to this page:

Please notify us if you found a problem with this document:

Other abuse

Documents from same domain

Fake News Detection on Social Media: A Data …

www.kdd.org

Fake News Detection on Social Media: A Data Mining Perspective Kai Shuy, Amy Slivaz, Suhang Wangy, Jiliang Tang \, and Huan Liuy yComputer Science & Engineering, Arizona State University, Tempe, AZ, USA

Social, Media, States, Data, Perspective, Mining, News, Detection, News detection on social media, A data, A data mining perspective

XGBoost: A Scalable Tree Boosting System

www.kdd.org

gradient tree boosting [10]1 is one technique that shines in many applications. Tree boosting has been shown to give state-of-the-art results on many standard classi cation benchmarks [16]. LambdaMART [5], a variant of tree boost-ing for ranking, achieves state-of-the-art result for ranking 1Gradient tree boosting is also known as gradient boosting

Boost, Boosting, Derating, Gradient boosting, Boost ing

Deep Crossing: Web-Scale Modeling without Manually …

www.kdd.org

Manually crafted combinatorial features have been the \se-cret sauce" behind many successful models. For web-scale applications, however, the variety and volume of features make these manually crafted features expensive to create, maintain, and deploy. This paper proposes the Deep Cross-ing model which is a deep neural network that automatically

Crafted

Graph Convolutional Matrix Completion

www.kdd.org

The decoder model is a pairwise decoder Aˇ = д(Z), which takes pairs of node embeddings (zi,zj)and predicts entries Aˇ ... Graph Convolutional Matrix Completion KDD’18 Deep Learning Day, August 2018, London, UK.

Decoder, Matrix, Deep, Completion, Graph, Convolutional, Graph convolutional matrix completion

“Why Should I Trust You?” Explaining the Predictions of ...

www.kdd.org

argue that explaining predictions is an important aspect in getting humans to trust and use machine learning e ectively, if the explanations are faithful and intelligible. The process of explaining individual predictions is illus-trated in Figure 1. It is clear that a doctor is much better positioned to make a decision with the help of a model if

Trust, Explaining, Prediction, Trust you, Explaining the predictions of

Collaborative Knowledge Base Embedding for Recommender …

www.kdd.org

network embedding method, termed as TransR, to extract items’ structural representations by considering the heterogeneity of both nodes and relationships. We apply stacked denoising auto-encoders and stacked convolutional auto-encoders, which are two types of deep learning based embedding techniques, to extract items’ tex-

Network, Structural, Deep, Embedding, Network embedding

Fake News Detection on Social Media: A Data Mining …

www.kdd.org

Fake News Detection on Social Media: A Data Mining Perspective Kai Shuy, Amy Slivaz, Suhang Wangy, Jiliang Tang \, and Huan Liuy yComputer Science & Engineering, Arizona State University, Tempe, AZ, USA zCharles River Analytics, Cambridge, MA, USA \Computer Science & Engineering, Michigan State University, East Lansing, MI, USA

Social, Media, Data, Perspective, Mining, News, Detection, News detection on social media, A data mining perspective, A data mining