Advanced Graph Neural Networks

Latest papers

• CHARM: A Multimodal Graph Foundation Model with Hierarchical Context Modeling for Zero-Shot Transfer

  Ankang Yang, Jitao Zhao, Di Jin, Yuxiao Huang, Dongxiao He · 29 July 2026

  Graph foundation models (GFMs) have emerged as a promising paradigm for transferring knowledge across graph domains and tasks. Real-world graphs associate nodes with text, images, and other modalities, making multimodal graphs essential for representing complex entities and relations. Moreover, coll…

• Learned, Relied Upon, or Necessary? Separating Checkpoint Dependence from Task-Level Value in Sheaf GNNs

  Yi Liu · 29 July 2026

  Learned restriction maps in sheaf graph neural networks are often treated as proof that the model has discovered useful edge geometry. That conclusion does not follow from parameter movement or from a post-hoc ablation: both can show how one checkpoint is organized while leaving open whether learned…

• CondPSE: A Polynomial-Filtered Structural Encoder with Conditional Modulation for Graphs

  Woohyun Lee, Hogun Park · 29 July 2026

  Message-passing graph neural networks are bounded by the 1-WL test and can miss topological structure that distinguishes non-isomorphic graphs. Positional and structural encodings (PSE) inject such topology-derived signals, and learned PSE encoders such as GPSE pretrain a single encoder to produce t…

• HeAD-CP: Heterophily-Aware Diffused Conformal Prediction Sets for Graph Neural Networks

  Phan Binh Nguyen Lam, Nguyen Thai Anh · 29 July 2026

  Conformal prediction (CP) provides distribution-free uncertainty quantification, and its extension to graphs is an active research direction. Diffused Adaptive Prediction Sets (DAPS) is a widely used graph-aware diffusion baseline, propagating Adaptive Prediction Sets (APS) non-conformity scores alo…

• A Survey of Graph Transformers: Architectures, Theories and Applications

  Chaohao Yuan, Kangfei Zhao, Ercan Engin Kuruoglu, Liang Wang, Tingyang Xu, Wenbing Huang, Deli Zhao, Hong Cheng, Yu Rong · 28 July 2026

  Graph Transformers (GTs) have demonstrated a strong capability in modeling graph structures by addressing the intrinsic limitations of graph neural networks (GNNs), such as over-smoothing and over-squashing. Recent studies have proposed diverse architectures, enhanced explainability, and practical a…

• What Softmax Throws Away: Mass-Aware Attention for Evidence Accumulation

  Minwoo Yu, Young-guk Ha · 28 July 2026

  High task performance does not show whether a model retains prediction-relevant structural information in its internal representation. Temporal graph models, for example, can achieve high future-link AUC while basic graph statistics remain difficult to recover from the same representation. We identi…

• Does Graph Compression Preserve Signal Propagation?

  Kawshik Banerjee, Khaled Mohammed Saifuddin · 28 July 2026

  Graph compression reduces the computational cost of graph learning, but its effect on signal propagation remains largely underexplored. Existing work evaluates compression through downstream task performance or structural preservation, neither of which directly captures how propagation dynamics chan…

• Unsupervised Graph Representation Learning with Complementary View Alignment

  Zengyi Wo, Shiyu Zhang, Qiyao Peng, Tianpeng Li, Xuan Guo · 28 July 2026

  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 ho…

• On a linear fused Gromov-Wasserstein distance for graph structured data

  Dai Hai Nguyen, Koji Tsuda · 28 July 2026

  We present a framework for embedding graph structured data into a vector space, taking into account node features and topology of a graph into the optimal transport (OT) problem. Then we propose a novel distance between two graphs, named linearFGW, defined as the Euclidean distance between their emb…

• Sheaf-Laplacian Obstruction and Projection Hardness for Cross-Modal Compatibility on a Modality-Independent Site

  Tibor Sloboda · 28 July 2026

  Cross-modal representations vary in how easily they can be aligned, and compatibility is generally non-transitive: two modalities may align through an intermediate modality at lower complexity than through a direct map. We introduce a reference formalism that evaluates all modalities on a fixed neig…

• When Can You Correct Distribution Drift in Temporal Graph Generation? A Sharpening--Drift Tension and an Impossibility for Observation-Based Correction

  Tianpeng Li, Xuan Guo, Wenjun Wang, Wang Zhang, Pengfei Jiao · 28 July 2026

  Generative models of temporal graphs are trained on one stretch of an evolving network and deployed on the next, and they degrade badly in the gap. We show this degradation is derivable, general, and not fixable from observations. The masked flow-matching loss decomposes exactly, with no independenc…

• A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction

  Nouhaila Innan, M. Murali Karthick, Simeon Kandan Sonar, Vivek Chaturvedi, Muhammad Shafique · 28 July 2026

  Dynamic link prediction is important for modeling evolving interactions in social, communication, financial, and transportation networks. Classical temporal graph models capture changes over time, but they may struggle to represent rapidly evolving node-edge interactions in large dynamic graphs. We …

• MA-DAR: Manifold-Aligned Dynamic Adaptive Routing for Continual Temporal Knowledge Graph Reasoning

  Xiangjun Shi, Chong Mu, Jinchuan Zhang, Lizong Zhang, Yuefeng He, Shang Liu · 27 July 2026

  Continual temporal knowledge graph (TKG) reasoning aims to continuously incorporate newly emerging facts while preserving previously acquired knowledge. Replay-based continual learning has achieved promising performance by revisiting historical representations. However, existing methods primarily fo…

• Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature

  Rachid Caich, Yassine Abbahaddou · 27 July 2026

  Curvature notions on graphs, particularly Ollivier-Ricci and Forman, have emerged as powerful tools for addressing fundamental issues in Graph Neural Networks (GNNs) such as oversmoothing and oversquashing, but rely almost exclusively on local edge-level comparisons and therefore fail to certify how…

• Towards Trustworthy and Cost-Efficient Data Integration: From Na\"ive RAG to Agentic RAG

  Chuangtao Ma, Arijit Khan · 27 July 2026

  Large language models (LLMs) and AI agents have demonstrated strong potential for data integration in zero-shot and few-shot settings. However, they continue to face significant accuracy and cost challenges in enterprise environments due to a persistent knowledge gap. This paper envisions trustworth…

• Remedying Coarsening-Based GNN Training under Heterophily via Adaptive Complementary Enhancement

  Guoming Li, Jian Yang, Xukun Wang, Zixiao Wang, Shangsong Liang, Yifan Chen · 27 July 2026

  Coarsening-based training for graph neural networks (GNNs), i.e.\ training on coarsened graphs rather than the original large ones, has become a promising direction for scaling GNNs to massive graphs. However, prior work has been evaluated almost exclusively on \textit{homophilic} graphs, leaving th…

• MotifRole-Diff: Risk-Optimal Role-Aware Corruption for Masked Molecular Graph Diffusion

  Tasfia Nuzhat Ornee, Elias Hossain, Ivan Garibay, Niloofar Yousef · 27 July 2026

  Masked discrete diffusion for molecular graph generation typically applies a uniform corruption schedule to all tokens in a lossless graph-to-sequence representation, implicitly treating structurally heterogeneous molecular components as equally difficult and equally important to reconstruct. Howeve…

• Spectral Flow Certificates for Depth-Aware Long-Range Propagation in Graph Neural Networks

  Ranjan Veerabhadraswamy, Ajith Jubilson Emerson · 27 July 2026

  Graph Neural Networks propagate information through local message passing, but the graph topologies themselves can silently prevent any amount of training from solving long-range tasks. When we deploy GNNs on new graphs, there is currently no inexpensive way to know, before training begins, whether …

• Efficient Recommendations via Graph Coarsening and Label Propagation

  Alessandro Sbandi, Federico Siciliano, Fabrizio Silvestri · 27 July 2026

  Graph-based recommendations are widely adopted in real-world industrial applications. However, graphs in these systems often reach a massive scale, posing notable scalability and efficiency challenges. This requires techniques that can effectively balance predictive quality with computational cost. …

• FrED: External Data Influence Estimation via Domain Knowledge Graph Grounding

  Theodoros Aivalis, Iraklis A. Klampanos, Antonis Troumpoukis, Joemon M. Jose · 27 July 2026

  The rapid deployment of generative AI has amplified the critical need for Training Data Attribution to ensure transparency and accountability. However, current parametric approaches require computationally prohibitive access to model weights, while similarity-based methods ignore deep structural con…

• Optimizing Hypergraph-Based RAG: Toward Better Fact Extraction and Chunk Retrieval

  Houda Khrouf, Pedro Fillastre, Sebastiao Correia · 24 July 2026

  GraphRAG enables deeper reasoning by structuring knowledge as graphs but struggles with n-ary facts. HyperGraphRAG uses hypergraphs for richer semantics, improving accuracy, yet relies on error-prone LLM extraction and inefficient standard chunk retrieval. We address this by employing self-consisten…

• Representing Entity Importance in AI Knowledge Systems: A Dual-Signal Framework of Audience Evaluation and Structural Authority

  Shen Xu · 24 July 2026

  AI knowledge systems require representations of entity importance for retrieval, recommendation, evidence selection, and knowledge-intensive reasoning. Yet importance is often reduced to a single score derived from either human response or graph structure. Such compression may discard distinctions t…

• Routing Without Training: Controllable-Ratio LLM Offloading via Reliability Gating

  Evan Chen, Shiqiang Wang, Kevin S Chan, Su Wang, Christopher Brinton · 24 July 2026

  Local-cloud collaboration is a practical way to deploy large language models under resource constraints, but existing methods often rely on trained routers or collaboration-aware finetuning that tie routing behavior to a particular operating regime. In this work, we show that such training may be un…

• Filter Learning for Subgraphs: Algebras and Performance Risk Bounds

  Purui Zhang, Feng Ji, Yanan Zhao, Bihan Wen, Wee Peng Tay · 24 July 2026

  Graph signal processing tasks that leverage spectral information typically assume access to the complete graph topology, which is often unavailable in practice. We propose a systematic framework for subgraph filter learning (SFL), where subgraph-supported operators approximate ambient graph filters …

• Semi-Supervised Text-Attributed Graph Distillation

  Yurui Lai, Samir Moustafa, Renchi Yang, Tsz Nam Chan · 24 July 2026

  {\em Text-Attributed Graphs} (TAGs) have emerged as an expressive data model for integrating graph topology with rich textual semantics. Existing representation learning methods over TAGs suffer from severe scalability bottlenecks, particularly together with {\em Large Language Models} (LLMs). While…