liu10961
这家伙很懒，什么也没写
Ta上传的资源 (0)
AAAI2017A Survey on Network Embedding
Modeling a sequence of interactions between users and items (e.g., products, posts, or courses) is crucial in domains such as e-commerce, social netwo
KDD2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks
Modelingsequentialinteractionsbetweenusersanditems/products
iscrucialindomainssuchase-commerce,socialnetworking,and
education.Representationlearningpr
KDD2018ArbitraryOrder Proximity Preserved Network Embedding
Networkembeddinghasreceivedincreasingresearchattentionin
recentyears.Theexistingmethodsshowthatthehigh-orderproximity
playsakeyroleincapturingtheund
On The Equivalence between Node Embeddings and Structural graph representations
Thisworkprovidesthefirstunifyingtheoreticalframeworkfornode(positional)
embeddingsandstructuralgraphrepresentations,bridgingmethodslikematrix
factor
ICLR2020Inductive representation learning on temporal graphs
Inductiverepresentationlearningontemporalgraphsisanimportantsteptoward
salablemachinelearningonreal-worlddynamicnetworks.Theevolvingnature
oftempora
CIKM2015GraRep Learning Graph Representation with Global Structural Information
Inthispaper,wepresentGraRep,anovelmodelforlearning
vertexrepresentationsofweightedgraphs.Thismodel
learnslowdimensionalvectorstorepresentverticesapp
KDD2016Structural Deep Network Embedding
Networkembeddingisanimportantmethodtolearnlow-dimensional
representationsofvertexesinnetworks,aimingtocaptureandpreserve
thenetworkstructure.Almosta
NIPS2019Selfattention with Functional Time Representation Learning
Sequentialmodellingwithself-attentionhasachievedcuttingedgeperformances
innaturallanguageprocessing.Withadvantagesinmodelflexibility,computation
compl
KDD2014DeepWalk online learning of social representations
WepresentDeepWalk,anovelapproachforlearninglatent
representationsofverticesinanetwork.Theselatent
representationsencodesocialrelationsinacontinuousv
ICLR2019DyREP Learing Representations over Dynamic Graphs
RepresentationLearningovergraphstructureddatahasreceivedsignificantattention
recentlyduetoitsubiquitousapplicability.However,mostadvancementshave
be