Beyond Homophily: Dual-Frequency Fusion for Multi-Label Node Classification

Multi-label node classification (MLNC) predicts multiple labels for each node in graph data, where connected nodes exhibit diverse label semantics, resulting in the coexistence of homogeneous and heterogeneous neighborhood information. Considering that homogeneous information preserves semantic consistency while heterogeneous one may harm consistency, existing methods mainly suppress heterogeneous neighbors while overlooking their potential discriminability. Integrating the merits of both information empowers representations but remains two coupled issues: (1) **Feature Entanglement.** Aggregating heterogeneous neighbors mixes different label semantics, resulting in ambiguous feature distributions and obscuring decision boundaries; (2) **Optimization Inconsistency.** These entangled features induce inconsistent prediction gradients among neighbors, making it difficult to reliably assign the contribution of neighborhood information. To mitigate these issues, we propose a Dual-Frequency Fusion Network (DF${}^2$Net), which realizes effective fusion of homogeneous and heterogeneous neighborhood information from a frequency perspective. Specifically, DF${}^2$Net models homogeneous and heterogeneous information as low- and high-frequency signals, respectively, and develops a dual-frequency fusion strategy to exploit their complementarity. Moreover, DF${}^2$Net introduces a Joint Representation-Optimization Consistency (JROC) module containing Label-guided Feature Refinement (LFR) and Gradient Consistency Calibration (GCC) to align representation and optimization spaces in a mutually reinforcing manner. LFR aligns node representations with relevant labels to disentangle ambiguous features and clear decision boundaries, yielding reliable prediction gradients. Based on the similarities of these gradients, GCC realizes to quantify optimization consistency and calibrate the fusion process. Through this synergy, DF${}^2$Net successfully exploits complementary homogeneous and heterogeneous information. Extensive experiments show that DF${}^2$Net achieves superior performance over state-of-the-art MLNC methods.