Tutorial at KDD 2018
Title: Graph and Tensor Mining for Fun and Profit
Xin Luna Dong (Amazon),
Christos Faloutsos (Amazon and CMU),
Andrey Kan (Amazon),
Subhabrata Mukherjee (Amazon), and
Jun Ma (Amazon)
Given a large graph, which is the most important node?
Can we plot and visualize the nodes in a low-dimensional space?
Given a heterogeneous graph (where edges have attributes),
like a knowledge graph, are there regularities? anomalies?
questions and several related ones, have attracted huge interest,
resulting in milestone algorithms like PageRank, HITS, recommendation systems,
`word2vec', and several more.
This tutorial surveys all these algorithms,
focusing on the intuition behind them
(as opposed to the mathematical analysis); it highlights
their strengths, similarities, and illustrates
their applicability to real-world problems.
FOILS - In single zip file
In single zip file (Caution: large - 26Mb)
FOILS - per individual part
Part 2: Tensors
- Part1.1 - properties
- Part1.2 - node importance
- Part1.3 - community detection
- Part1.4 - anomaly detection
- Part1.5 - belief propagation
- Part2.1 - tensors - basics
- Part2.2 - embeddings
- Part2.3 - inference
Last updated: Aug. 13, 2018, by Christos Faloutsos