This perspectiveparallels an earlier phenomenon inthe much better understood field of optimization where convexity has played a preponderant role for both theoretical and methodological advances [Nes04; Bub15].

Our goal is to provide a systematic understanding of the landscape of graph neural networks for knowledge graphs pertaining to the prominent task of link prediction. Our analysis entails a unifying perspective on seemingly unrelated models and unlocks a series of other models.

Inboth cases, weestablish that the number of calls to the stochastic first-order oracle to obtain an appropriately definedϵ-stationary point isoftheorderO(1/ϵ2.5).