TGB-Seq provides eight low-repetition temporal graph datasets and shows that current temporal GNNs struggle to capture sequential dynamics, generalizing poorly to unseen edges.
Sentence-BERT: Sentence embeddings using Siamese BERT- networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics
TGB-Seq provides eight low-repetition temporal graph datasets and shows that current temporal GNNs struggle to capture sequential dynamics, generalizing poorly to unseen edges.