Entity interference from new knowledge graph entities causes up to 25% overestimation of CKGE method performance by disrupting prior predictions, requiring a corrected evaluation protocol.
Acontinualknowledgegraphembeddingmethodbasedonlocal-globaldistillation, in: 2025 8th International Symposium on Big Data and Applied Statistics (ISBDAS), IEEE
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Revisiting Catastrophic Forgetting in Continual Knowledge Graph Embedding
Entity interference from new knowledge graph entities causes up to 25% overestimation of CKGE method performance by disrupting prior predictions, requiring a corrected evaluation protocol.