Advanced Graph Neural Networks

Derniers papiers

• Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks?

  Yuhang Ma, Jie Wang, Zheng Yan · 30 mars 2026

  Large Language Models (LLMs) have advanced Graph Neural Networks (GNNs) by enriching node representations with semantic features, giving rise to LLM-enhanced GNNs that achieve notable performance gains. However, the robustness of these models against poisoning attacks, which manipulate both graph st…

• PEANUT: Perturbations by Eigenvalue Alignment for Attacking GNNs Under Topology-Driven Message Passing

  Bhavya Kohli, Biplab Sikdar · 30 mars 2026

  Graph Neural Networks (GNNs) have achieved remarkable performance on tasks involving relational data. However, small perturbations to the graph structure can significantly alter GNN outputs, raising concerns about their robustness in real-world deployments. In this work, we explore the core vulnerab…

• On the Complexity of Optimal Graph Rewiring for Oversmoothing and Oversquashing in Graph Neural Networks

  Mostafa Haghir Chehreghani · 30 mars 2026

  Graph Neural Networks (GNNs) face two fundamental challenges when scaled to deep architectures: oversmoothing, where node representations converge to indistinguishable vectors, and oversquashing, where information from distant nodes fails to propagate through bottlenecks. Both phenomena are intimate…

• Methods for Knowledge Graph Construction from Text Collections: Development and Applications

  Vanni Zavarella · 30 mars 2026

  Virtually every sector of society is experiencing a dramatic growth in the volume of unstructured textual data that is generated and published, from news and social media online interactions, through open access scholarly communications and observational data in the form of digital health records an…

• Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow

  Jicheng Ma, Yunyan Yang, Juan Zhao, Liang Zhao · 30 mars 2026

  We introduce the Geometric Evolution Graph Convolutional Network (GEGCN), a novel framework that enhances graph representation learning by modeling geometric evolution on graphs. Specifically, GEGCN employs a Long Short-Term Memory to model the structural sequence generated by discrete Ricci flow, a…

• DyMRL: Dynamic Multispace Representation Learning for Multimodal Event Forecasting in Knowledge Graph

  Feng Zhao, Kangzheng Liu, Teng Peng, Yu Yang, Guandong Xu · 27 mars 2026

  Accurate representation of multimodal knowledge is crucial for event forecasting in real-world scenarios. However, existing studies have largely focused on static settings, overlooking the dynamic acquisition and fusion of multimodal knowledge. 1) At the knowledge acquisition level, how to learn tim…

• Graph Memory: A Structured and Interpretable Framework for Modality-Agnostic Embedding-Based Inference

  Artur A. Oliveira, Mateus Espadoto, Roberto M. Cesar Jr., Roberto Hirata Jr · 27 mars 2026

  We introduce Graph Memory (GM), a structured non-parametric framework that represents an embedding space through a compact graph of reliability-annotated prototype regions. GM encodes local geometry and regional ambiguity through prototype relations and performs inference by diffusing query evidence…

• UniAI-GraphRAG: Synergizing Ontology-Guided Extraction, Multi-Dimensional Clustering, and Dual-Channel Fusion for Robust Multi-Hop Reasoning

  Jie Wang, Honghua Huang, Xi Ge, Jianhui Su, Wen Liu, Shiguo Lian · 27 mars 2026

  Retrieval-Augmented Generation (RAG) systems face significant challenges in complex reasoning, multi-hop queries, and domain-specific QA. While existing GraphRAG frameworks have made progress in structural knowledge organization, they still have limitations in cross-industry adaptability, community …

• DAGverse: Building Document-Grounded Semantic DAGs from Scientific Papers

  Shu Wan, Saketh Vishnubhatla, Iskander Kushbay, Tom Heffernan, Aaron Belikoff, Raha Moraffah, Huan Liu · 27 mars 2026

  Directed Acyclic Graphs (DAGs) are widely used to represent structured knowledge in scientific and technical domains. However, datasets for real-world DAGs remain scarce because constructing them typically requires expert interpretation of domain documents. We study Doc2SemDAG construction: recoveri…

• Circuit Complexity of Hierarchical Knowledge Tracing and Implications for Log-Precision Transformers

  Naiming Liu, Richard Baraniuk, Shashank Sonkar · 26 mars 2026

  Knowledge tracing models mastery over interconnected concepts, often organized by prerequisites. We analyze hierarchical prerequisite propagation through a circuit-complexity lens to clarify what is provable about transformer-style computation on deep concept hierarchies. Using recent results that l…

• Cost-Sensitive Neighborhood Aggregation for Heterophilous Graphs: When Does Per-Edge Routing Help?

  Eyal Weiss · 26 mars 2026

  Recent work distinguishes two heterophily regimes: adversarial, where cross-class edges dilute class signal and harm classification, and informative, where the heterophilous structure itself carries useful signal. We ask: when does per-edge message routing help, and when is a uniform spectral channe…

• Reservoir-Based Graph Convolutional Networks

  Mayssa Soussia, Gita Ayu Salsabila, Mohamed Ali Mahjoub, Islem Rekik · 26 mars 2026

  Message passing is a core mechanism in Graph Neural Networks (GNNs), enabling the iterative update of node embeddings by aggregating information from neighboring nodes. Graph Convolutional Networks (GCNs) exemplify this approach by adapting convolutional operations for graph structures, allowing fea…

• Causality-Driven Disentangled Representation Learning in Multiplex Graphs

  Saba Nasiri, Selin Aviyente, Dorina Thanou · 26 mars 2026

  Learning representations from multiplex graphs, i.e., multi-layer networks where nodes interact through multiple relation types, is challenging due to the entanglement of shared (common) and layer-specific (private) information, which limits generalization and interpretability. In this work, we intr…

• CGRL: Causal-Guided Representation Learning for Graph Out-of-Distribution Generalization

  Bowen Lu, Liangqiang Yang, Teng Li · 26 mars 2026

  Graph Neural Networks (GNNs) have achieved impressive performance in graph-related tasks. However, they suffer from poor generalization on out-of-distribution (OOD) data, as they tend to learn spurious correlations. Such correlations present a phenomenon that GNNs fail to stably learn the mutual inf…

• TuneShift-KD: Knowledge Distillation and Transfer for Fine-tuned Models

  Yushi Guan, Jeanine Ohene-Agyei, Daniel Kwan, Jean Sebastien Dandurand, Yifei Zhang, Nandita Vijaykumar · 26 mars 2026

  To embed domain-specific or specialized knowledge into pre-trained foundation models, fine-tuning using techniques such as parameter efficient fine-tuning (e.g. LoRA) is a common practice. However, as new LLM architectures and pre-trained models emerge, transferring this specialized knowledge to new…

• HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature

  Devvrat Joshi, Islem Rekik · 25 mars 2026

  Automated knowledge graph (KG) construction is essential for navigating the rapidly expanding body of scientific literature. However, existing approaches struggle to recognize long multi-word entities, often fail to generalize across domains, and typically overlook the hierarchical nature of scienti…

• Graph Variate Neural Networks

  Om Roy, Yashar Moshfeghi, Keith Smith · 25 mars 2026

  Modelling dynamically evolving spatio-temporal signals is a prominent challenge in the Graph Neural Network (GNN) literature. Notably, GNNs assume an existing underlying graph structure. While this underlying structure may not always exist or is derived independently from the signal, a temporally ev…

• Q-AGNN: Quantum-Enhanced Attentive Graph Neural Network for Intrusion Detection

  Devashish Chaudhary, Sutharshan Rajasegarar, Shiva Raj Pokhrel · 25 mars 2026

  With the rapid growth of interconnected devices, accurately detecting malicious activities in network traffic has become increasingly challenging. Most existing deep learning-based intrusion detection systems treat network flows as independent instances, thereby failing to exploit the relational dep…

• Can Graph Foundation Models Generalize Over Architecture?

  Benjamin Gutteridge, Michael Bronstein, Xiaowen Dong · 25 mars 2026

  Graph foundation models (GFMs) have recently attracted interest due to the promise of graph neural network (GNN) architectures that generalize zero-shot across graphs of arbitrary scales, feature dimensions, and domains. While existing work has demonstrated this ability empirically across diverse re…

• A One-Inclusion Graph Approach to Multi-Group Learning

  Noah Bergam, Samuel Deng, Daniel Hsu · 25 mars 2026

  We prove the tightest-known upper bounds on the sample complexity of multi-group learning. Our algorithm extends the one-inclusion graph prediction strategy using a generalization of bipartite $b$-matching. In the group-realizable setting, we provide a lower bound confirming that our algorithm's $\l…

• Graphs RAG at Scale: Beyond Retrieval-Augmented Generation With Labeled Property Graphs and Resource Description Framework for Complex and Unknown Search Spaces

  Manie Tadayon, Mayank Gupta · 25 mars 2026

  Recent advances in Retrieval-Augmented Generation (RAG) have revolutionized knowledge-intensive tasks, yet traditional RAG methods struggle when the search space is unknown or when documents are semi-structured or structured. We introduce a novel end-to-end Graph RAG framework that leverages both La…

• ABSTRAL: Automatic Design of Multi-Agent Systems Through Iterative Refinement and Topology Optimization

  Weijia Song, Jiashu Yue, Zhe Pang · 25 mars 2026

  How should multi-agent systems be designed, and can that design knowledge be captured in a form that is inspectable, revisable, and transferable? We introduce ABSTRAL, a framework that treats MAS architecture as an evolving natural-language document, an artifact refined through contrastive trace ana…

• Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation Learning

  Haifang Cao, Yu Wang, Timing Li, Xinjie Yao, Pengfei Zhu · 25 mars 2026

  Graph-structured data typically exhibits complex topological heterogeneity, making it difficult to model accurately within a single Riemannian manifold. While emerging mixed-curvature methods attempt to capture such diversity, they often rely on implicit, task-driven routing that lacks fundamental g…

• Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation

  Michal Balcerak, Suprosana Shit, Chinmay Prabhakar, Sebastian Kaltenbach, Michael S. Albergo, Yilun Du, Bjoern Menze · 25 mars 2026

  Energy-based models for discrete domains, such as graphs, explicitly capture relative likelihoods, naturally enabling composable probabilistic inference tasks like conditional generation or enforcing constraints at test-time. However, discrete energy-based models typically struggle with efficient an…

• GraphRAG for Engineering Diagrams: ChatP&ID Enables LLM Interaction with P&IDs

  Achmad Anggawirya Alimin, Artur M. Schweidtmann · 25 mars 2026

  Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG) and knowledge graphs offer new opportunities for interacting with engineering diagrams such as Piping and Instrumentation Diagrams (P&IDs). However, directly processing raw images or smart P&ID files with LLMs is often c…