ToLL pretrains 3D scene graph generators via anchor-conditioned topological layout recovery and asymmetric structural distillation to learn predicate constraints rather than geometric interpolation shortcuts.
Graph con- trastive learning with augmentations
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
CP-GBA distills a queryable repository of promptable subgraph triggers via graph prompt learning to achieve transferable backdoor attacks on GNNs with state-of-the-art success rates across paradigms and defenses.
citing papers explorer
-
ToLL: Topological Layout Learning with Asymmetric Cross-View Structural Distillation for 3D Scene Graph Generation Pretraining
ToLL pretrains 3D scene graph generators via anchor-conditioned topological layout recovery and asymmetric structural distillation to learn predicate constraints rather than geometric interpolation shortcuts.
-
Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers
CP-GBA distills a queryable repository of promptable subgraph triggers via graph prompt learning to achieve transferable backdoor attacks on GNNs with state-of-the-art success rates across paradigms and defenses.