Wikipedia

By M. Contreras, A. Posadas, José María Gutiérrez, Pedro F. Miret. 2008

Subfields: Knowledge Graphs & Representation

How researchers see this paper

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

In Knowledge Graphs & Representation

1. Fuzhen Zhuang
2. Hui Xiong
3. Qing He
4. Hengshu Zhu
5. Chuan Qin
6. Qingyu Guo
7. Xing Xie
8. Roland Memisevic

Citations in the corpus

• Federated Machine Learning (2019, background): “For example, the recent data breach by Facebook has caused a wide range of protests [70].”
• Protection Against Reconstruction and Its Applications in Private Federated Learning (2018, methodology): “We pretrain an LSTM on Wikipedia data [67] taken from October 1, 2016.”
• Randomized Distributed Mean Estimation: Accuracy vs. Communication (2016, methodology): “We can then use a variant of variable-length quantity [11] to represent the set { ( j s − j s − 1 , Y i ( j s )) } ks =1 .”
• The “Something Something” Video Database for Learning and Evaluating Visual Common Sense (2017, background): “Closely related to material properties is the notion of af-fordance [36, 9]: An object can, by virtue of its properties, be used to perform certain actions, and often this usability is more important than its “true” inherent object class (which may itself be considered a questionable concept [9]).”
• Horovod: fast and easy distributed deep learning in TensorFlow (2018, background): “…the most of our GPU capacity, we became even more excited about distributed training after Facebook published a paper [6], demonstrating training of a ResNet-50 network in one hour on 256 GPUs by combining principles of data parallelism [7] with an innovative learning rate adjustment technique.”
• Learning One-hidden-layer Neural Networks with Landscape Design (2017, background): “Let H j be the probabilists’ Hermite polynomial [Wik17b], and let h j = 1 √ j !”
• Trial without Error: Towards Safe Reinforcement Learning via Human Intervention (2017, background): “Microsoft’s chatbot Tay reproduced thousands of offensive tweets before being taken down [29].”
• SoK: Consensus in the Age of Blockchains (2017, background): “It is also possible to store the blockchain as a tree-like structure called the hash tree or the Merkle tree [135].”
• Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment (2016, background): “Multilingual knowledge bases such as Wikipedia [Wikipedia, 2017], WordNet [Bond and Foster, 2013], and Concept-Net [Speer and Havasi, 2013] are becoming essential sources of knowledge for people and AI-related applications.”
• WikiLinkGraphs: A complete, longitudinal and multi-language dataset of the Wikipedia link networks (2019, background): “The English version alone has more than 5.7 million articles and 46 million pages and is edited on average by more than 128k active users every month (MediaWiki developers 2018).”
• Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation (2019, methodology): “In our experiment, we use Meshlab [6] to generate level-1 icosahedron [47] vertices coordinates and corresponding edges for deformation hypotheses and local GCN graph topology.”
• Style in the Age of Instagram: Predicting Success within the Fashion Industry using Social Media (2015, methodology): “We collected data from the Fashion Model Directory (FMD) website, one of the largest fashion databases of professional female fashion models [45].”
• Ex Machina: Personal Attacks Seen at Scale (2016, methodology): “In order to obtain these, we enhance our random dataset by also sampling comments made by users who where blocked for violating Wikipedia’s policy on personal attacks [33].”