Advanced Graph Neural Networks

Derniers papiers

• Knowledge Graph Re-engineering Along the Ontological Continuum (extended version)

  Enrico Daga, Valentina Tamma, Terry Payne · 26 mai 2026

  Knowledge graphs have become the primary vehicle for data integration and are critical to the success of modern AI, but the diversity of KG modelling practices, from lightweight vocabularies to richly axiomatised ontologies, makes integration and reuse expensive and brittle. This challenge is partic…

• Gaussian Rank-Based Neighborhood Degree for Graph Neural Networks in Image Classification

  Rafael Mendon\c{c}a Duarte, Jean Roberto Ponciano, Lucas Pascotti Valem · 26 mai 2026

  The exponential growth of data has intensified the gap between the availability of unlabeled data and the high cost of manual annotation. Graph Neural Networks (GNNs) have emerged as a promising solution, as they exploit relational structures and learn from both labeled and unlabeled data, performin…

• Clustering as Reasoning: A $k$-Means Interpretation of Chain-of-Thought Graph Learning

  Xuanting Xie, Zhaochen Guo, Bingheng Li, Xingtong Yu, Zhifei Liao, Zhao Kang, Yuan Fang · 26 mai 2026

  Chain-of-Thought (CoT) prompting has shown promise in enhancing the reasoning capabilities of large language models (LLMs) on text-attributed graphs (TAGs). This work reframes CoT-based graph learning through the principle of clustering as reasoning, offering a $k$-means interpretation of how iterat…

• Efficient and Scalable Neural Symbolic Search for Knowledge Graph Complex Query Answering

  Weizhi Fei, Zihao Wang, hang Yin, Shukai Zhao, Wei Zhang, Yangqiu Song · 26 mai 2026

  Complex Query Answering (CQA) is a crucial reasoning task over Knowledge Graphs (KGs), which aims to answer first-order logical queries from incomplete KGs. While existing neural-symbolic methods achieve strong performance, they face significant complexity bottlenecks: quadratic data complexity scal…

• 'Si'multaneous 'S'patial-'T'emporal Message Passing for Dynamic Graph Representation Learning

  Shubhajit Roy, Anirban Dasgupta · 26 mai 2026

  Dynamic graph neural networks (DGNNs) that operate on snapshot sequences typically fall into one of two categories. \emph{Temporal-first} approaches build per-node temporal embeddings and only afterwards perform spatial aggregation, whereas \emph{Spatial-first} approaches invert this order, feeding …

• Closed-Form Node Classification with Exact Graph Unlearning

  Aditya Gaur, Charu Sharma · 26 mai 2026

  Graph neural networks for node classification are typically trained by gradient descent over hundreds or thousands of epochs. Recent work has shown that, when properly tuned, classic GCN/SAGE/GAT architectures can match graph transformers on many node-classification benchmarks. We ask a complementar…

• Advancing Graph Few-Shot Learning via In-Context Learning

  Renchu Guan, Yajun Wang, Chunli Guo, Bowen Cao, Fausto Giunchiglia, Wei Pang, Yonghao Liu, Xiaoyue Feng · 26 mai 2026

  Graph few-shot learning, which aims to classify nodes from novel classes with only a few labeled examples, is a widely studied problem in graph learning. However, existing methods often face two key limitations. First, the predominant graph few-shot learning paradigm relies on supervised tasks, fail…

• Lattice theory and algebraic models for deep convolutional learning based on mathematical morphology

  Gustavo (Jesus), Angulo · 26 mai 2026

  We develop a rigorous algebraic framework for deep convolutional architectures, CNNs, ResNets, and encoder--decoder networks such as UNet, grounded in lattice theory and mathematical morphology. The central tool is the Matheron--Maragos--Banon--Barrera (MMBB) universal representation theory for tran…

• Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs

  Hao Yan, Xuanru Wang, Jun Yin, Shirui Pan, Senzhang Wang, Chengqi Zhang · 26 mai 2026

  Multimodal Attributed Graph Learning (MAGL) integrates intrinsic node attributes with structural topology via graph aggregation. However, as pretrained encoders evolve into Large Foundation Models (LFMs), the landscape of MAGL fundamentally shifts: under high-confidence LFM priors, mandatory aggrega…

• MDGMIX: Boundary-Aware Subgraph Mixing for Multi-Domain Graph Pre-Training

  Ziyu Zheng, Yaming Yang, Ziyu Guan, Wei Zhao, Xinyan Huang · 26 mai 2026

  Multi-domain graph pre-training is a crucial step in constructing foundational graph models with cross-domain generalization capabilities. However, existing methods predominantly rely on jointly training all source domain graphs, resulting in high computational costs. Furthermore, it remains unclear…

• Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach

  Yujing Liu, Yixin Liu, Yu Zheng, Alan Wee-Chung Liew, Xiaofeng Cao, Shirui Pan · 26 mai 2026

  Generalist graph anomaly detection (GAD) aims to detect anomalies on unseen graphs without graph-specific retraining. Nevertheless, existing approaches primarily focus on aligning heterogeneous features across different data domains via PCA-based projection, which harmonizes feature dimensions ignor…

• AvAtar: Learning to Align via Active Optimal Transport

  Qi Yu, Ruizhong Qiu, Zhichen Zeng, My T. Thai, Huan Liu, Hanghang Tong · 26 mai 2026

  Alignment plays a fundamental role in many machine learning problems, such as multi-network analysis, multimodal learning, and point cloud registration. Recent works increasingly leverage optimal transport (OT) for distributional alignment, whose effectiveness largely depends on sparse supervision t…

• Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion

  Jaejun Lee, Seheon Kim, Joyce Jiyoung Whang · 26 mai 2026

  Hyper-relational knowledge graphs (HKGs) effectively represent complex facts. While inferring new knowledge in HKGs is a critical problem, current methods cast it as a simple link prediction, assuming that nearly all entities and relations within a fact are known, leaving only a single blank to be f…

• HiTeC: Hierarchical Contrastive Learning on Text-Attributed Hypergraph with Semantic-Aware Augmentation

  Mengting Pan, Fan Li, Chen Chen, Xiaoyang Wang, Wenjie Zhang · 26 mai 2026

  Contrastive learning (CL) has become a dominant paradigm for self-supervised hypergraph learning, enabling effective training without costly labels. However, node entities in real-world hypergraphs are often associated with rich textual information, which has been largely ignored in prior works. Dir…

• L2IR: Revealing Latent Intent in Graph Fraud Detection

  Jinsheng Guo, Zhenhao Weng, Yibo Liu, Yan Qiao, Meng Li · 26 mai 2026

  Graph fraud detection has long depended on Graph Neural Networks (GNNs) to propagate and aggregate information across relational data. A critical obstacle in practice, however, is that fraudsters frequently disguise themselves by forging numerous connections with benign users, causing fraud signals …

• BoxLitE: A Faithful Knowledge Base Embedding Based on Convex Optimization

  Bruno F. Louren\c{c}o, Hesham Morgan, Ana Ozaki, Aleksandar Pavlovi\'c, Emanuel Sallinger · 26 mai 2026

  Knowledge base (KB) embeddings aim at combining the capability of classical knowledge graph embeddings to generalize the information present in facts, the ABox, with conceptual knowledge represented in an ontology language, the TBox. Several authors have recently explored the idea of mapping concept…

• Invariant-Based Weight Sharing for Message Passing

  Florian Seiffarth · 26 mai 2026

  Message-passing neural networks (MPNNs) are a powerful framework for learning representations of graph-structured domains. However, weights in MPNNs act on features only, limiting their ability to capture structural patterns. We introduce a novel structure-aware weight sharing principle that explici…

• 'Si'multaneous 'S'patial-'T'emporal Message Passing for Dynamic Graph Representation Learning

  Shubhajit Roy, Anirban Dasgupta · 26 mai 2026

  Dynamic graph neural networks (DGNNs) that operate on snapshot sequences typically fall into one of two categories. \emph{Temporal-first} approaches build per-node temporal embeddings and only afterwards perform spatial aggregation, whereas \emph{Spatial-first} approaches invert this order, feeding …

• Neural Scalable Symbolic Search Framework for Complex Logical Queries with Multiple Free Variables

  Weizhi Fei, Hang Yin, Zihao Wang, Shukai Zhao, Wei Zhang, Yangqiu Song · 26 mai 2026

  Complex Query Answering (CQA) is a fundamental knowledge representation and reasoning task over incomplete knowledge graphs (KGs). Answering existential first-order queries with $k$ free variables (i.e., $\text{EFO}_k$ queries) is a crucial yet challenging problem, as it requires ranking answer tupl…

• LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs

  Sanchit Kabra, Nikhil Abhyankar, Saaketh Desai, Prasad Iyer, Chandan K Reddy · 26 mai 2026

  Scientific discovery is a closed-loop process in which hypotheses guide data acquisition and observations refine the hypothesis space. Yet most approaches reduce discovery to supervised learning over fixed datasets, where limited observations can support multiple plausible mechanisms that fit locall…

• Incorporating Deep Learning Design in Database Queries

  Yuval Lev Lubarsky, Dean Light, Boaz Berger, Shunit Agmon, Benny Kimelfeld · 26 mai 2026

  Deep learning over relational databases is conventionally realized by translating data into graph representations and applying graph-based neural networks within external frameworks. This round-trip between the database and external machine learning (ML) systems introduces non-trivial engineering ov…

• Knowledge Graph-Driven Expert-Level Reasoning for Neuroscience

  Jake Stephen, Niraj K. Jha · 26 mai 2026

  Knowledge graph (KG) is an abstraction that can be extracted from text corpora and used for in-depth reasoning. Prior work has leveraged KGs to fine-tune language models (LMs), enabling domain-specific superintelligence. In this work, we explore whether KG-driven in-depth reasoning capabilities can …

• Treatment Effect Estimation with Differentiated Networked Effect on Graph Data

  Xiaofeng Lin, Han Bao, Hisashi Kashima · 26 mai 2026

  Estimating individual treatment effect (ITE) from observational graph data is crucial for decision-making in the fields such as commerce and medicine. This task is challenging due to interference, where individual outcomes can be influenced by the treatments and covariates of their neighbors. Existi…

• Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation

  Zichao Yue, Zhiru Zhang · 26 mai 2026

  Pre-propagation graph neural networks (PPGNNs) decouple node feature propagation from transformation: graph diffusion is performed once as preprocessing, and training reduces to dense per-node transformations. This design enables mini-batch training without inter-node dependencies, avoids repeated s…

• Learning manifold diffusion semigroups from graph transition matrices

  Xiuyuan Cheng, Nan Wu · 26 mai 2026

  We consider graph diffusion processes constructed from finite i.i.d. samples drawn from an unknown manifold embedded in ambient Euclidean space, where the graph affinity is defined by an ambient Gaussian kernel matrix. We show that the manifold heat semigroup $Q_t = e^{t\Delta}$ can be approximated …