THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model

arXiv:2607.27303v1 Announce Type: cross Abstract: Temporal heterogeneous graphs offer a natural abstraction for dynamic relational systems in which diverse node and relation types co-exist and evolve over time. Learning on such graphs requires jointly modeling cross-type structural heterogeneity and the temporal dynamics of interactions, yet existing methods still struggle to reconcile parameter-efficient cross-type transfer with relation-aware specialization, and typically inject time only as additive features outside the attention kernel. We propose extbf{THGFM}, a web-scale temporal heterogeneous graph fusion model that addresses both limitations within a unified dual-path architecture. THGFM couples a extit{Shared-Space Temporal Attention} branch for parameter-efficient cross-type transfer with a extit{Relational Type-Partitioned Temporal Attention} branch for relation-aware specialization, and integrates them through extit{Dual-Path Relational--Shared Fusion}, instantiated with extit{Type-Conditioned Non-Competitive Gated Sum Fusion}: a adaptive mechanism that assigns independent, type-conditioned feature-wise gates to the shared and specialized branches, allowing both to be amplified or suppressed without zero-sum competition. To directly incorporate relative time into the attention score, THGFM further introduces extit{Rotary Temporal Attention}, which rotates queries and keys by half-phases of relative time before matching. THGFM consistently outperforms baseline graph transformer models on academic graphs benchmarks, delivering a +3.25% six-task mean gain, with peak relative gains of +12.37% on OAG-CS PV, +4.87% on PF-L_2, and +1.18% on PF-L_1, and +4.24%, +3.73%, and +4.61% on OGBN-MAG, HTAG-ArXiv, and HTAG-DBLP, respectively.

Source: arXiv cs.CL | 2026-07-31

Related