Contrastive Variational Graph Symmetric Autoencoder for Full Extrapolation Over Temporal Knowledge Graphs

Temporal knowledge graph (TKG) reasoning is potent for discovering plausible facts with observable knowledge. However, evolving TKGs often bring newly unseen entities, relations, and timestamps, which pose significant challenges for current TKG reasoning methods as they struggle to extrapolate facts involving unseen components. We term this realistic yet under-investigated problem as full extrapolation over TKGs, aiming to model all unseen components for reasoning within evolving TKGs. To tackle this, we propose a novel contrastive variational graph symmetric autoencoder (CVGSAE) framework under the meta-learning setting. Initially, we first extract the spatiotemporal connections between relations and integrate a functional time encoding strategy to simultaneously initialize unseen entities, relations, and timestamps. Subsequently, we design an interactive variational graph symmetric autoencoder to encode and then reconstruct entity and relation representations by capturing their interactions to generate contrastive views. Finally, a dual-contrastive learning scheme is imposed on the encoded and reconstructed representations of both entities and relations to enhance their discriminability and task relevance. Extensive experiments on two benchmark datasets demonstrate that CVGSAE yields significant advancements beyond state-of-the-art baselines across all evaluation metrics. The source code is available at:https://github.com/hcfun/CVGSAE