Advanced Graph Neural Networks

Derniers papiers

• Information Geometry of Absorbing Markov-Chain and Discriminative Random Walks

  Masanari Kimura · 10 février 2026

  Discriminative Random Walks (DRWs) are a simple yet powerful tool for semi-supervised node classification, but their theoretical foundations remain fragmentary. We revisit DRWs through the lens of information geometry, treating the family of class-specific hitting-time laws on an absorbing Markov ch…

• Efficient Graph Knowledge Distillation from GNNs to Kolmogorov--Arnold Networks via Self-Attention Dynamic Sampling

  Can Cui, Zilong Fu, Penghe Huang, Yuanyuan Li, Wu Deng, Dongyan Li · 10 février 2026

  Recent success of graph neural networks (GNNs) in modeling complex graph-structured data has fueled interest in deploying them on resource-constrained edge devices. However, their substantial computational and memory demands present ongoing challenges. Knowledge distillation (KD) from GNNs to MLPs o…

• FairRARI: A Plug and Play Framework for Fairness-Aware PageRank

  Emmanouil Kariotakis, Aritra Konar · 10 février 2026

  PageRank (PR) is a fundamental algorithm in graph machine learning tasks. Owing to the increasing importance of algorithmic fairness, we consider the problem of computing PR vectors subject to various group-fairness criteria based on sensitive attributes of the vertices. At present, principled algor…

• Rethinking Graph Generalization through the Lens of Sharpness-Aware Minimization

  Yang Qiu, Yixiong Zou, Jun Wang · 10 février 2026

  Graph Neural Networks (GNNs) have achieved remarkable success across various graph-based tasks but remain highly sensitive to distribution shifts. In this work, we focus on a prevalent yet under-explored phenomenon in graph generalization, Minimal Shift Flip (MSF),where test samples that slightly de…

• Compact Conformal Subgraphs

  Sreenivas Gollapudi, Kostas Kollias, Kamesh Munagala, Aravindan Vijayaraghavan · 10 février 2026

  Conformal prediction provides rigorous, distribution-free uncertainty guarantees, but often yields prohibitively large prediction sets in structured domains such as routing, planning, or sequential recommendation. We introduce "graph-based conformal compression", a framework for constructing compact…

• Retrieval Pivot Attacks in Hybrid RAG: Measuring and Mitigating Amplified Leakage from Vector Seeds to Graph Expansion

  Scott Thornton · 10 février 2026

  Hybrid Retrieval-Augmented Generation (RAG) pipelines combine vector similarity search with knowledge graph expansion for multi-hop reasoning. We show that this composition introduces a distinct security failure mode: a vector-retrieved "seed" chunk can pivot via entity links into sensitive graph ne…

• USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptation

  Yingxu Wang, Kunyu Zhang, Mengzhu Wang, Siyang Gao, Nan Yin · 10 février 2026

  SF-GDA is pivotal for privacy-preserving knowledge transfer across graph datasets. Although recent works incorporate structural information, they implicitly condition adaptation on the smoothness priors of sourcetrained GNNs, thereby limiting their generalization to structurally distinct targets. Th…

• Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering

  Yunhui Liu, Pengyu Qiu, Yu Xing, Yongchao Liu, Peng Du, Chuntao Hong, Jiajun Zheng, Tao Zheng, Tieke He · 10 février 2026

  Attributed Graph Clustering (AGC) is a fundamental unsupervised task that integrates structural topology and node attributes to uncover latent patterns in graph-structured data. Despite its significance in industrial applications such as fraud detection and user segmentation, a significant chasm per…

• TFMLinker: Universal Link Predictor by Graph In-Context Learning with Tabular Foundation Models

  Tianyin Liao, Chunyu Hu, Yicheng Sui, Xingxuan Zhang, Peng Cui, Jianxin Li, Ziwei Zhang · 10 février 2026

  Link prediction is a fundamental task in graph machine learning with widespread applications such as recommendation systems, drug discovery, knowledge graphs, etc. In the foundation model era, how to develop universal link prediction methods across datasets and domains becomes a key problem, with so…

• SCOUT-RAG: Scalable and Cost-Efficient Unifying Traversal for Agentic Graph-RAG over Distributed Domains

  Longkun Li, Yuanben Zou, Jinghan Wu, Yuqing Wen, Jing Li, Hangwei Qian, Ivor Tsang · 10 février 2026

  Graph-RAG improves LLM reasoning using structured knowledge, yet conventional designs rely on a centralized knowledge graph. In distributed and access-restricted settings (e.g., hospitals or multinational organizations), retrieval must select relevant domains and appropriate traversal depth without …

• LIT-GRAPH: Evaluating Deep vs. Shallow Graph Embeddings for High-Quality Text Recommendation in Domain-Specific Knowledge Graphs

  Nirmal Gelal, Chloe Snow, Kathleen M. Jagodnik, Ambyr Rios, Hande K\"u\c{c}\"uk McGinty · 10 février 2026

  This study presents LIT-GRAPH (Literature Graph for Recommendation and Pedagogical Heuristics), a novel knowledge graph-based recommendation system designed to scaffold high school English teachers in selecting diverse, pedagogically aligned instructional literature. The system is built upon an onto…

• Laplacian-LoRA: Delaying Oversmoothing in Deep GCNs via Spectral Low-Rank Adaptation

  Sai Vamsi Alisetti · 10 février 2026

  Oversmoothing is a fundamental limitation of deep graph convolutional networks (GCNs), causing node representations to collapse as depth increases. While many prior approaches mitigate this effect through architectural modifications or residual mechanisms, the underlying spectral cause of oversmooth…

• Dense Neural Networks are not Universal Approximators

  Levi Rauchwerger, Stefanie Jegelka, Ron Levie · 10 février 2026

  We investigate the approximation capabilities of dense neural networks. While universal approximation theorems establish that sufficiently large architectures can approximate arbitrary continuous functions if there are no restrictions on the weight values, we show that dense neural networks do not p…

• Learning to Select: Query-Aware Adaptive Dimension Selection for Dense Retrieval

  Zhanyu Wu, Richong Zhang, Zhijie Nie · 10 février 2026

  Dense retrieval represents queries and documents as high-dimensional embeddings, but these representations can be redundant at the query level: for a given information need, only a subset of dimensions is consistently helpful for ranking. Prior work addresses this via pseudo-relevance feedback (PRF)…

• Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks

  Yu-Che Tsai, Hsiang Hsiao, Kuan-Yu Chen, Shou-De Lin · 10 février 2026

  Text embeddings enable numerous NLP applications but face severe privacy risks from embedding inversion attacks, which can expose sensitive attributes or reconstruct raw text. Existing differential privacy defenses assume uniform sensitivity across embedding dimensions, leading to excessive noise an…

• TAAM:Inductive Graph-Class Incremental Learning with Task-Aware Adaptive Modulation

  Jingtao Liu, Xinming Zhang · 10 février 2026

  Graph Continual Learning (GCL) aims to solve the challenges of streaming graph data. However, current methods often depend on replay-based strategies, which raise concerns like memory limits and privacy issues, while also struggling to resolve the stability-plasticity dilemma. In this paper, we sugg…

• Is Meta-Path Attention an Explanation? Evidence of Alignment and Decoupling in Heterogeneous GNNs

  Maiqi Jiang, Noman Ali, Yiran Ding, Yanfu Zhang · 10 février 2026

  Meta-path-based heterogeneous graph neural networks aggregate over meta-path-induced views, and their semantic-level attention over meta-path channels is widely used as a narrative for ``which semantics matter.'' We study this assumption empirically by asking: when does meta-path attention reflect m…

• Predicting Graph Structure via Adapted Flux Balance Analysis

  Sevvandi Kandanaarachchi, Ziqi Xu, Stefan Westerlund, Conrad Sanderson · 10 février 2026

  Many dynamic processes such as telecommunication and transport networks can be described through discrete time series of graphs. Modelling the dynamics of such time series enables prediction of graph structure at future time steps, which can be used in applications such as detection of anomalies. Ex…

• Negative-Aware Diffusion Process for Temporal Knowledge Graph Extrapolation

  Yanglei Gan, Peng He, Yuxiang Cai, Run Lin, Guanyu Zhou, Qiao Liu · 10 février 2026

  Temporal Knowledge Graph (TKG) reasoning seeks to predict future missing facts from historical evidence. While diffusion models (DM) have recently gained attention for their ability to capture complex predictive distributions, two gaps remain: (i) the generative path is conditioned only on positive …

• Drop the mask! GAMM-A Taxonomy for Graph Attributes Missing Mechanisms

  Richard Serrano (LabHC), Baptiste Jeudy (LabHC), Charlotte Laclau (IDS, S2A), Christine Largeron (LabHC) · 10 février 2026

  Exploring missing data in attributed graphs introduces unique challenges beyond those found in tabular datasets. In this work, we extend the taxonomy for missing data mechanisms to attributed graphs by proposing GAMM (Graph Attributes Missing Mechanisms), a framework that systematically links missin…

• Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought?

  Alexander von Recum, Leander Girrbach, Zeynep Akata · 10 février 2026

  Reasoning LLMs (RLLMs) generate step-by-step chains of thought (CoTs) before giving an answer, which improves performance on complex tasks and makes reasoning more transparent. But how robust are these reasoning traces to disruptions that occur within them? To address this question, we introduce a c…

• GCN-MPPR: Enhancing the Propagation of Message Passing Neural Networks via Motif-Based Personalized PageRank

  Mingcan Wang, Junchang Xin, Zhongming Yao, Kaifu Long, Zhiqiong Wang · 10 février 2026

  The algorithms based on message passing neural networks (MPNNs) on graphs have recently achieved great success for various graph applications. However, studies find that these methods always propagate the information to very limited neighborhoods with shallow depth, particularly due to over-smoothin…

• Graph homophily booster: Reimagining the role of discrete features in heterophilic graph learning

  Ruizhong Qiu, Ting-Wei Li, Gaotang Li, Hanghang Tong · 10 février 2026

  Graph neural networks (GNNs) have emerged as a powerful tool for modeling graph-structured data. However, existing GNNs often struggle with heterophilic graphs, where connected nodes tend to have dissimilar features or labels. While numerous methods have been proposed to address this challenge, they…

• Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning

  Nikunj Gupta, James Zachary Hare, Rajgopal Kannan, Viktor Prasanna · 10 février 2026

  This paper presents deep meta coordination graphs (DMCG) for learning cooperative policies in multi-agent reinforcement learning (MARL). Coordination graph formulations encode local interactions and accordingly factorize the joint value function of all agents to improve efficiency in MARL. Through D…

• Fast and Simple Densest Subgraph with Predictions

  Thai Bui, Luan Nguyen, Hoa T. Vu · 10 février 2026

  We study the densest subgraph problem and its variants through the lens of learning-augmented algorithms. We show that, given a reasonably accurate predictor that estimates whether a node belongs to the densest subgraph (e.g., a machine-learning classifier), one can design simple and practical linea…