alibaba / alibaba/euler

DeepWalk和Line的性能差异

Open
#174 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
2.9k
Forks
553
PR merge metrics
No merged PRs in 30d

Description

想请教一下,在我的数据集上,DeepWalk的效果远好于Line(2nd order)。DeepWalk离线mrr可以达到0.7+, Line只有0.2+,二者都是无监督Loss。想请教下,这种情况是什么原因呢?我的graph是item同构图,node百万,连边亿级。谢谢。

Contributor guide

No contributing guide indexed for this repository

Research direction

No source file, test, or entry point is named. First identify the DeepWalk and LINE (2nd-order) implementations and compare their training objectives and graph sampling on the stated million-node, hundred-million-edge item graph. Done would require a project-grounded explanation for the reported MRR gap.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.