Gumbel-softmax-based optimization: a simple general framework for optimization problems on graphs
Abstract In computer science, there exist a large number of optimization problems defined on graphs, that is to find a best node state configuration or a network structure, such that the designed objective function is optimized under some constraints. However, these problems are notorious for their...
Main Authors: | Yaoxin Li, Jing Liu, Guozheng Lin, Yueyuan Hou, Muyun Mou, Jiang Zhang |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2021-02-01
|
Series: | Computational Social Networks |
Subjects: | |
Online Access: | https://doi.org/10.1186/s40649-021-00086-z |
Similar Items
-
Topic-Document Inference With the Gumbel-Softmax Distribution
by: Amit Kumar, et al.
Published: (2021-01-01) -
On the Softmax Bottleneck of Word-Level Recurrent Language Models
by: Parthiban, Dwarak Govind
Published: (2020) -
Personalized Online Live Video Streaming Using Softmax-Based Multinomial Classification
by: Kyeongseon Kim, et al.
Published: (2019-06-01) -
The Exponentiated Generalized Gumbel Distribution
by: THIAGO ANDRADE, et al.
Published: (2015-01-01) -
The Gumbel-Lomax Distribution: Properties and Applications
by: M.H. Tahir, et al.
Published: (2016-02-01)