QUIET is a hierarchical RVQ-based graph tokenizer with a learned level-weighting gate; it improves several benchmarks but not consistently against the strongest baselines.
Neural common neighbor with comple- tion for link prediction.arXiv preprint arXiv:2302.00890
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
citing papers explorer
-
A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning
QUIET is a hierarchical RVQ-based graph tokenizer with a learned level-weighting gate; it improves several benchmarks but not consistently against the strongest baselines.
- ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery