One-for-All Community Search on Unseen Graphs

ECHO: Adaptive Community Search over Multimodal Graphs

In this paper, for the first time, we study the community search problem over multimodal graphs. This task aims to identify a query vertex-containing subgraph that is both structurally cohesive and semantically coherent with multimodal query inputs (e.g., text and images). Existing community search methods fail to capture fine-grained multimodal semantics and do not support effective multimodal fusion. To address these limitations, we propose an adaptive community search framework ECHO, which includes two key components. (i) A Fine-grained Modality Extractor decomposes multimodal content into structured local semantic units to preserve details often lost in coarse representations, operating in an encoder-agnostic manner. (ii) A Dual-Track Mixture of Experts network decouples semantic and structural modeling into parallel tracks, utilizing a hierarchical MoE architecture for adaptive, query-aware feature fusion. Extensive experiments on real-world multimodal graphs demonstrate that ECHO consistently outperforms state-of-the-art methods in terms of community quality while achieving superior search efficiency.

GAAF: Fast and Scalable Graph-based Vector Similarity Search with Any-Match Label Filtering

GAAF, a frequency-aware Graph Ensemble framework that decouples the handling of high- and low-frequency labels, is proposed, a frequency-aware Graph Ensemble framework that significantly outperforms state-of-the-art baselines.

Similarity-Guided Structural Matching Learning for Graph Dataset Condensation

Similarity-guided Structural Matching Learning for Graph Dataset Condensation (SSGDC) is proposed, which efficiently reduces repository size while maintaining both task performance and structural information.

HGOOD : Hypergraph-enhanced Graph Contrastive Learning for Graph Out-of-Distribution Detection

GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) over knowledge graphs requires retrievers that can effectively capture both graph structure and semantic information. Recent approaches have explored graph neural network (GNN)-based retrievers to model graph topology in multi-hop reasoning tasks. In parallel, graph language models (GLMs) have emerged as a promising paradigm that integrates graph reasoning and the semantic capabilities of language models. In this work, we introduce a GLM-based retriever and investigate the comparative strengths of GLM-based, GNN-based, and traditional vector-search-based retrievers in single- and multi-hop RAG settings, and with a particular focus on transferability to unseen domains. Our findings suggest that finetuned GLM retrievers generalize better out of domain, achieving SOTA on two multi-hop benchmarks. On in-domain multi-hop QA datasets they remain comparable to prior work, with promising scaling as parameters and subgraph coverage increase. GNN-based retrievers achieve higher graph coverage with an efficient training setup, whereas the vector-search baseline excels at single-hop datasets.

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.