高效的时间图学习：算法、框架与工具 Towards Efficient Temporal Graph Learning-Algorithms, Frameworks, and Tools.docx

TowardsEfficientTemporalGraphLearning:

Algorithms,Frameworks,andTools

RuijieWangWanyuZhaoDachunSunCharithMendisTarekAbdelzaher

UniversityofIllinoisUrbana-Champaign

{ruijiew2,wanyu2,dsun18,charithm,zaher}@I

Time:1:45PM-17:30PM,October21,2024

Location:Room120C,BoiseCentre,Boise,ID

Webpage:https://wjerry5.github.io/cikm2024-tutorial/

Contents

?PartI-Introduction

?PartII-Data-EfficientTemporalGraphNeuralNetwork

?30-minCoffeeBreak

?PartIII-Resource-EfficientTemporalGraphNeuralNetwork

?PartIV-DiscussionandFutureDirections

3

Part

PartI-IntroductionPartII-Data-EfficientTGNNPartIII-Resource-EfficientTGNNPartIV-DiscussionFuture

BroadApplicationDomainsofGraphData

SocialNetworkAnalysisKnowledgeGraphReasoningWebMining

RecommendationScientificDiscoveryLLMPromptingReasoning

Universal

Universallanguagefordescribinginterconnecteddata!

4

Part

PartI-IntroductionPartII-Data-EfficientTGNNPartIII-Resource-EfficientTGNNPartIV-DiscussionFuture

Real-WorldGraphsareEvolving–TemporalGraphs

TemporalFactsinKGs

MolecularDynamics

UserOnlineBehaviors

DynamicalSystems

Part

PartI-IntroductionPartII-Data-EfficientTGNNPartIII-Resource-EfficientTGNNPartIV-DiscussionFuture

Real-WorldGraphsareEvolving–TemporalGraphs

oGraphshavetime-evolvingcomponents,e.g.,

oTopologystructures

oAdd/deletenodes

oAdd/deleteedges

oInputfeatures

oNode-levelfeatures

oEdge-levelfeatureso…

Dynamicedges[1]Dynamicnodeset[2]

Dynamicnodeedgefeatures[3]

[1]/temporal-graph-networks-ab8f327f2efe.

[2]Wanget.al.,LearningtoSampleandAggregate:Few-shotReasoningoverTemporalKnowledgeGraphs