SOTAVerified

Graph Generation

Graph Generation is an important research area with significant applications in drug and material designs.

Source: Graph Deconvolutional Generation

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 361–370 of 712 papers

TitleStatusHype
Domain-wise Invariant Learning for Panoptic Scene Graph Generation—0
Doubly Reparameterized Importance Weighted Structure Learning for Scene Graph Generation—0
Dual Embodied-Symbolic Concept Representations for Deep Learning—0
Dual ResGCN for Balanced Scene GraphGeneration—0
Dynamic Graph Generation Network: Generating Relational Knowledge from Diagrams—0
Dynamic Relation Transformer for Contextual Text Block Detection—0
Dynamic Scene Graph Generation via Anticipatory Pre-Training—0
EDGE++: Improved Training and Sampling of EDGE—0
EDoG: Adversarial Edge Detection For Graph Neural Networks—0
Effective Decoding in Graph Auto-Encoder using Triadic Closure—0
Show:102550
← PrevPage 37 of 72Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RNNStreetMover0.03—Unverified
2GraphRNNStreetMover0.02—Unverified
3GGT without CAStreetMover0.02—Unverified
4GGTStreetMover0.02—Unverified