Introduction to Graph Neural Networks. Synthesis Lectures on Artificial Intelligence and Machine Learning, Morgan & Claypool Publishers, 2020. book Zhiyuan Liu, Jie Zhou. Graph Neural Networks: A Review of Methods and Applications. AI Open 2020. paper Jie Zhou, Ganqu Cui, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Maosong Sun. A Comprehensive Survey on Graph Neural Networks. arxiv 2019. paper Zongha
近年、Google, Apple, Facebook, Amazonなど、世界を代表する企業で研究されている分析手法があります。それがグラフニューラルネットワーク(GNN)です。GNNは現在ではビジネスで結果を出す段階にまで進化を遂げてきました。 今回はGNNとは何かから、実際にどのような結果を出しているかを紹介します。 GNNとは何かグラフニューラルネットワーク (GNN) とは、グラフ上の問題を扱うニューラルネットワークです。 グラフとは、以下のノードとエッジから成るデータ構造を示します。 ・ノード:何かの対象を表す ・エッジ:ノード同士を結び、関係性を表す このグラフの使用例として、GNNでは以下のものがあります。 ・コミュニティ:ノード→人、エッジ→友人関係 ・交通:ノード→地点、エッジ→ルート ・化合物:ノード→原子、エッジ→結合 Graph Neural Networks: M
Graphs are commonly used in different real-world applications. Social networks are large graphs of people that follow each other, biologists use graphs of protein interactions, while communication networks are graphs themselves. They use graphs of word co-occurrences in the field of text mining. The interest in performing machine learning on graphs is growing. They try to predict new friendships i
The latest news from Google on open source releases, major projects, events, and student outreach programs. Logica: organizing your data queries, making them universally reusable and fun We present Logica, a novel open source Logic Programming language. A successor to Yedalog (a language developed at Google earlier) it is a Datalog-like logic programming language. Logica code compiles to SQL and r
the morning paper a random walk through Computer Science research, by Adrian Colyer Made delightfully fast by strattic Learning a unified embedding for visual search at Pinterest Zhai et al., KDD’19 Last time out we looked at some great lessons from Airbnb as they introduced deep learning into their search system. Today’s paper choice highlights an organisation that has been deploying multiple dee
At Pinterest, we utilize image embeddings throughout our search and recommendation systems to help our users navigate through visual content by powering experiences like browsing of related content and searching for exact products for shopping. In this work we describe a multi-task deep metric learning system to learn a single unified image embedding which can be used to power our multiple visual
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く