Bridging Feature-structural Homophily and Long-range Heterogeneity for Self-supervised Heterogeneous Graph Learning

Unsupervised Graph Representation Learning with Complementary View Alignment

Unsupervised graph representation learning aims to derive meaningful node embeddings by capturing both structural and attribute information without relying on labeled data. Existing methods, such as GAEs, have demonstrated effectiveness but typically rely on message-passing mechanisms that assume homophily, leading to performance degradation on heterophilous graphs, where connected nodes exhibit dissimilar features. This homophily bias results in the loss of critical high-frequency components that are essential for identifying heterophilous patterns. To address these challenges, we propose \textsc{AlignGAE}, a novel extension of \textit{MaskGAE} that preserves the full frequency spectrum through complementary view alignment. Our framework introduces a dual-encoder architecture that separately processes structural and attribute information, incorporates node positional encoding to approximate Neighborhood Identity Distribution (NID), and employs dual reconstruction tasks for both edges and node attributes. We further propose theoretically grounded NID alignment strategies that ensure semantic consistency across views while preserving their distinct characteristics. Through comprehensive spectral analysis, we demonstrate that \textsc{AlignGAE} achieves optimal representation properties when the alignment loss converges. Extensive experiments across 12 benchmark datasets validate our approach, showing that \textsc{AlignGAE} outperforms state-of-the-art methods by up to 18.7\% on heterophilous graphs in node classification, while maintaining competitive performance on homophilous graphs. Our results establish a new paradigm for frequency-aware graph representation learning.

Disentangled Hypergraph Network with Implicit Structure Learning for Mobility Social Relationship Inference

D2GSL: Self-Supervised Dual-Layer Structure-Driven Graph Structure Learning

: Graph structure learning depends heavily on the integrity and reliability of graph data. However, real-world graphs often contain noise, missing information, and bias, thereby limiting the expressive capacity of existing models. Single-layer structure learning methods fail to simultaneously capture local interactions and the global structure. Furthermore, they rely excessively on high-quality labeled data, leading to label scarcity issues and high annotation costs. To address these challenges, we propose a self-supervised dual-layer structure-driven graph structure learning method, termed D2GSL. Specifically, D2GSL constructs a semantic similarity channel and a spectral feature channel to model node relationships from both local semantic and global spectral views. It introduces a hyperadjacency matrix that explicitly models inter-layer node correspondences and enables joint structural reconstruction across channels. The framework further applies structural reconstruction constraints and adopts a contrastive learning mechanism to enhance structural representations in a self-supervised setting. Comprehensive experimental results demonstrate that D2GSL consistently outperforms mainstream baseline models on public benchmark datasets and exhibits remarkable efficacy under label-scarcity conditions.

Heterophily-Aware Node Classification in Multiplex Graphs

Structure-Feature Aligned Graph Learning via Alternating Constrained Optimization

This work presents a constrained two-view learning framework for robust graph learning, which aligns structure-aware GNN embeddings with a structure-free feature prior and designs a channel-split adaptive gated layer within DSAL to effectively integrate this prior.

HGAT-Rec: a hierarchical graph attention framework for cross-domain e-commerce recommendation with heterogeneity-aware contrastive alignment

Cross-domain recommendation over heterogeneous e-commerce networks faces three unresolved technical failures: existing GNN recommenders apply a single shared attention vector across all neighbor pairs, which can introduce a type-conflation bias governed by the inter-type variance of attention coefficients; meta-path importance weights learned in a source domain become systematically miscalibrated under the relational distribution shift of cross-domain transfer; and contrastive learning methods apply type-agnostic perturbations that assign equal dropout intensity to semantically distinct edge types, degrading representation quality in heterogeneous graph settings. We propose HGAT-Rec, which incorporates a heterogeneity-aware contrastive learning (HCL) objective that grounds view construction and sample selection in the typed relational structure of a cross-domain heterogeneous graph: type-stratified edge dropout preserves high-signal interaction channels proportionally to their attention weight, type-conditioned positive samples are drawn from meta-path neighborhoods sharing genuine relational content, and a cross-domain InfoNCE term enforces relative ordering constraints across the full overlapping user population. To support HCL, HGAT-Rec further provides (i) a type-triple-indexed graph attention mechanism parameterized by the joint combination of source node type, target node type, and edge type; (ii) a domain-conditioned meta-path aggregation layer with separate per-domain path importance distributions sharing a domain-invariant query vector; and (iii) a TransR-based knowledge gated fusion module decoupling item semantics from interaction sparsity. Theoretical grounding is provided by two formal propositions characterizing type-conflation bias and contrastive robustness under sparsity. Experiments on the Amazon Product Co-purchasing benchmark show that HGAT-Rec outperforms eleven baselines, achieving 11.20% and 8.70% improvements in NDCG@10 and HR@10 over the strongest competitor, a 31.80% gain for cold-start users, and a sparsity degradation rate of 35.2% under 80% interaction removal versus 49.0% for the next-best baseline.