Advanced Graph Neural Networks

Derniers papiers

• Controllable Reasoning Models Are Private Thinkers

  Haritz Puerto, Haonan Li, Xudong Han, Timothy Baldwin, Iryna Gurevych · 2 mars 2026

  AI agents powered by reasoning models require access to sensitive user data. However, their reasoning traces are difficult to control, which can result in the unintended leakage of private information to external parties. We propose training models to follow instructions not only in the final answer…

• Rudder: Steering Prefetching in Distributed GNN Training using LLM Agents

  Aishwarya Sarkar, Sayan Ghosh, Nathan Tallent, Aman Chadha, Tanya Roosta, Ali Jannesari · 2 mars 2026

  Large-scale Graph Neural Networks (GNNs) are typically trained by sampling a vertex's neighbors to a fixed distance. Because large input graphs are distributed, training requires frequent irregular communication that stalls forward progress. Moreover, fetched data changes with graph, graph distribut…

• Normalisation and Initialisation Strategies for Graph Neural Networks in Blockchain Anomaly Detection

  Dang Sy Duy, Nguyen Duy Chien, Kapil Dev, Jeff Nijsse · 2 mars 2026

  Graph neural networks (GNNs) offer a principled approach to financial fraud detection by jointly learning from node features and transaction graph topology. However, their effectiveness on real-world anti-money laundering (AML) benchmarks depends critically on training practices such as specifically…

• Leveraging Non-linear Dimension Reduction and Random Walk Co-occurrence for Node Embedding

  Ryan DeWolfe · 2 mars 2026

  Leveraging non-linear dimension reduction techniques, we remove the low dimension constraint from node embedding and propose COVE, an explainable high dimensional embedding that, when reduced to low dimension with UMAP, slightly increases performance on clustering and link prediction tasks. The embe…

• MMKG-RDS: Reasoning Data Synthesis via Deep Mining of Multimodal Knowledge Graphs

  Lun Zhan, Feng Xiong, Huanyong Liu, Feng Zhang, Yuhui Yin · 2 mars 2026

  Synthesizing high-quality training data is crucial for enhancing domain models' reasoning abilities. Existing methods face limitations in long-tail knowledge coverage, effectiveness verification, and interpretability. Knowledge-graph-based approaches still fall short in functionality, granularity, c…

• Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning

  Dawei Cheng, Wenjun Wang, Mingjian Guang · 2 mars 2026

  Graph neural networks (GNNs) have become a standard paradigm for graph representation learning, yet their message passing mechanism implicitly assumes that messages can be represented by source node embeddings, an assumption that fails in heterophilic graphs. While existing methods attempt to addres…

• Geodesic Semantic Search: Learning Local Riemannian Metrics for Citation Graph Retrieval

  Brandon Yee, Lucas Wang, Kundana Kommini, Krishna Sharma · 2 mars 2026

  We present Geodesic Semantic Search (GSS), a retrieval system that learns node-specific Riemannian metrics on citation graphs to enable geometry-aware semantic search. Unlike standard embedding-based retrieval that relies on fixed Euclidean distances, \gss{} learns a low-rank metric tensor $\mL_i \i…

• A Theory of Random Graph Shift in Truncated-Spectrum vRKHS

  Zhang Wan, Tingting Mu, Samuel Kaski · 2 mars 2026

  This paper develops a theory of graph classification under domain shift through a random-graph generative lens, where we consider intra-class graphs sharing the same random graph model (RGM) and the domain shift induced by changes in RGM components. While classic domain adaptation (DA) theories have…

• Flowette: Flow Matching with Graphette Priors for Graph Generation

  Asiri Wijesinghe, Sevvandi Kandanaarachchi, Daniel M. Steinberg, Cheng Soon Ong · 2 mars 2026

  We study generative modeling of graphs with recurring subgraph motifs. We propose Flowette, a continuous flow matching framework, that employs a graph neural network based transformer to learn a velocity field defined over graph representations with node and edge attributes. Our model preserves topo…

• MUG: Meta-path-aware Universal Heterogeneous Graph Pre-Training

  Lianze Shan, Jitao Zhao, Dongxiao He, Yongqi Huang, Zhiyong Feng, Weixiong Zhang · 27 février 2026

  Universal graph pre-training has emerged as a key paradigm in graph representation learning, offering a promising way to train encoders to learn transferable representations from unlabeled graphs and to effectively generalize across a wide range of downstream tasks. However, recent explorations in u…

• DyGnROLE: Modeling Asymmetry in Dynamic Graphs with Node-Role-Oriented Latent Encoding

  Tyler Bonnet, Marek Rei · 27 février 2026

  Real-world dynamic graphs are often directed, with source and destination nodes exhibiting asymmetrical behavioral patterns and temporal dynamics. However, existing dynamic graph architectures largely rely on shared parameters for processing source and destination nodes, with limited or no systemati…

• Comparative Analysis of Neural Retriever-Reranker Pipelines for Retrieval-Augmented Generation over Knowledge Graphs in E-commerce Applications

  Teri Rumble, Zbyn\v{e}k Gazd\'ik, Javad Zarrin, Jagdeep Ahluwalia · 27 février 2026

  Recent advancements in Large Language Models (LLMs) have transformed Natural Language Processing (NLP), enabling complex information retrieval and generation tasks. Retrieval-Augmented Generation (RAG) has emerged as a key innovation, enhancing factual accuracy and contextual grounding by integratin…

• Tokenization, Fusion and Decoupling: Bridging the Granularity Mismatch Between Large Language Models and Knowledge Graphs

  Siyue Su, Jian Yang, Bo Li, Guanglin Niu · 27 février 2026

  Leveraging Large Language Models (LLMs) for Knowledge Graph Completion (KGC) is promising but hindered by a fundamental granularity mismatch. LLMs operate on fragmented token sequences, whereas entities are the fundamental units in knowledge graphs (KGs) scenarios. Existing approaches typically cons…

• LEDA: Latent Semantic Distribution Alignment for Multi-domain Graph Pre-training

  Lianze Shan, Jitao Zhao, Dongxiao He, Siqi Liu, Jiaxu Cui, Weixiong Zhang · 27 février 2026

  Recent advances in generic large models, such as GPT and DeepSeek, have motivated the introduction of universality to graph pre-training, aiming to learn rich and generalizable knowledge across diverse domains using graph representations to improve performance in various downstream applications. How…

• Persistent Nonnegative Matrix Factorization via Multi-Scale Graph Regularization

  Jichao Zhang, Ran Miao, Limin Li · 27 février 2026

  Matrix factorization techniques, especially Nonnegative Matrix Factorization (NMF), have been widely used for dimensionality reduction and interpretable data representation. However, existing NMF-based methods are inherently single-scale and fail to capture the evolution of connectivity structures a…

• IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck

  Tian Bian, Yifan Niu, Chaohao Yuan, Chengzhi Piao, Bingzhe Wu, Long-Kai Huang, Yu Rong, Tingyang Xu, Hong Cheng, Jia Li · 27 février 2026

  Circuit discovery has recently attracted attention as a potential research direction to explain the non-trivial behaviors of language models. It aims to find the computational subgraphs, also known as circuits, within the model that are responsible for solving specific tasks. However, most existing …

• ECHO: Encoding Communities via High-order Operators

  Emilio Ferrara · 27 février 2026

  Community detection in attributed networks faces a fundamental divide: topological algorithms ignore semantic features, while Graph Neural Networks (GNNs) encounter devastating computational bottlenecks. Specifically, GNNs suffer from a Semantic Wall of feature over smoothing in dense or heterophili…

• Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hulls

  Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas, Michail Chatzianastasis, Giannis Nikolentzos · 26 février 2026

  Representation learning has been essential for graph machine learning tasks such as link prediction, community detection, and network visualization. Despite recent advances in achieving high performance on these downstream tasks, little progress has been made toward self-explainable models. Understa…

• NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training

  Zhongwei Xie, Jiaxin Bai, Shujie Liu, Haoyu Huang, Yufei Li, Yisen Gao, Hong Ting Tsang, Yangqiu Song · 26 février 2026

  Neural Graph Databases (NGDBs) facilitate complex logical reasoning over incomplete knowledge structures, yet their training efficiency and expressivity are constrained by rigid query-level batching and structure-exclusive embeddings. We present NGDB-Zoo, a unified framework that resolves these bott…

• RABot: Reinforcement-Guided Graph Augmentation for Imbalanced and Noisy Social Bot Detection

  Longlong Zhang, Xi Wang, Haotong Du, Yangyi Xu, Zhuo Liu, Yang Liu · 26 février 2026

  Social bot detection is pivotal for safeguarding the integrity of online information ecosystems. Although recent graph neural network (GNN) solutions achieve strong results, they remain hindered by two practical challenges: (i) severe class imbalance arising from the high cost of generating bots, an…

• Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling

  Guancheng Tu, Shiyang Zhang, Tianyu Zhang, Yi Zhang, Diji Yang · 26 février 2026

  Large Language Models (LLMs) are converging towards a singular Artificial Hivemind, where shared Nature (pre-training priors) result in a profound collapse of distributional diversity, limiting the distinct perspectives necessary for creative exploration and scientific discovery. To address this, we…

• DRESS: A Continuous Framework for Structural Graph Refinement

  Eduar Castrillo Velilla · 25 février 2026

  The Weisfeiler-Lehman (WL) hierarchy is a cornerstone framework for graph isomorphism testing and structural analysis. However, scaling beyond 1-WL to 3-WL and higher requires tensor-based operations that scale as O(n^3) or O(n^4), making them computationally prohibitive for large graphs. In this pa…

• CITED: A Decision Boundary-Aware Signature for GNNs Towards Model Extraction Defense

  Bolin Shen, Md Shamim Seraj, Zhan Cheng, Shayok Chakraborty, Yushun Dong · 25 février 2026

  Graph neural networks (GNNs) have demonstrated superior performance in various applications, such as recommendation systems and financial risk management. However, deploying large-scale GNN models locally is particularly challenging for users, as it requires significant computational resources and e…

• Hierarchical Molecular Representation Learning via Fragment-Based Self-Supervised Embedding Prediction

  Jiele Wu, Haozhe Ma, Zhihan Guo, Thanh Vinh Vo, Tze Yun Leong · 25 février 2026

  Graph self-supervised learning (GSSL) has demonstrated strong potential for generating expressive graph embeddings without the need for human annotations, making it particularly valuable in domains with high labeling costs such as molecular graph analysis. However, existing GSSL methods mostly focus…

• Position-Aware Sequential Attention for Accurate Next Item Recommendations

  Timur Nabiev, Evgeny Frolov · 25 février 2026

  Sequential self-attention models usually rely on additive positional embeddings, which inject positional information into item representations at the input. In the absence of positional signals, the attention block is permutation-equivariant over sequence positions and thus has no intrinsic notion o…