Advanced Graph Neural Networks

Derniers papiers

• Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks

  Fabian Hoppe, Melven R\"ohrig-Z\"ollner, Philipp Knechtges · 2 juin 2026

  We consider LLM-based algorithm development through a case study on contractionorder optimisation for tensor networks with OpenEvolve. We pay particular attention to the choice of the LLM as well as design choices such as evaluation metric and test instances. Our results highlight both the promise o…

• Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learning

  Zian Zhai, Fan Li, Xingyu Tan, Xiaoyang Wang, Wenjie Zhang · 2 juin 2026

  Vector Quantization (VQ) has recently emerged as a promising approach for learning compressed and discrete representations for graph-structured data. However, a fundamental challenge, i.e., codebook collapse, remains underexplored in the graph domain, significantly limiting the expressiveness and ge…

• Consistency evaluation of benchmarks used for causal discovery

  Yuzhe Zhang, Chihui Chen, Lina Yao, Chen Wang · 2 juin 2026

  In graphical causal model, causal discovery aims to construct a causal graph based on numerical data and domain knowledge in plain text. However, the evaluation of causal discovery methods remains a challenge in the area as the progress of domain researches often makes benchmark causal graphs contai…

• Absorbing Complexity: An Interaction-Native Knowledge Harness for Financial LLM Agents

  Ailiya Borjigin, Igor Stadnyk, Ben Bilski, Maksym Chikita, Dmytro Kyrylenko, Sofiia Pidturkina, Julia Stadnyk · 2 juin 2026

  Financial AI agents often fail for a simple reason: they make users carry the complexity. A user must repeatedly restate goals, risk preferences, portfolio context, past judgments, and shifting market assumptions, while the agent answers, retrieves, acts, and forgets. In finance, this is not just in…

• AdaKernel: Learning Adaptive Kernel Parameters for Spatiotemporal Graph Neural Networks

  Zhongyue Zhang, Guangyin Jin, Yuxuan Liang, Suwan Yin, Yuankai Wu · 2 juin 2026

  Modeling spatial dependencies is central to spatiotemporal data analysis using Graph Neural Networks (GNNs). Traditional methods rely on distance-based kernels with predefined parameters, which restricts model capacity. Although generic adaptive mechanisms (e.g., Graph Attention Networks) offer flex…

• GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks

  Canyixing Cui, Tao Wu, Xingping Xian, Xiao-Ke Xu, Mao Wang, Weina Niu · 2 juin 2026

  Graph Neural Networks (GNNs) are vulnerable to adversarial attacks, which inherently invert connectivity patterns by introducing disassortative edges in assortative graphs and assortative edges in disassortative graphs. This structural inversion creates structure-feature mismatches that disrupt neig…

• TechGraphRAG: An Agentic Graph-Augmented RAG Framework for Technical Literature Reasoning

  Kanwar Bharat Singh · 2 juin 2026

  This paper presents an agentic retrieval-augmented generation (RAG) framework for domain-specific technical reasoning support, instantiated over a curated corpus of approximately 2,100 academic papers in intelligent tires, vehicle dynamics, and vehicle control. Unlike conventional single-pass RAG sy…

• Construction of Historical Knowledge Graphs Based on BERT and Graph Neural Networks

  Ping Li, Bartlomiej Brzozka · 2 juin 2026

  Through digital humanities research and scale-up historical data analysis, a significant amount of traditional historical text is converted into structured knowledge graphs. This paper provides a high-level architecture that combines bidirectional encoder representations of transformers (BERT) and g…

• COPF: An Online Framework for Deployment-Stable Counterfactual Fairness in Evolving Graphs

  Sheng'en Li, Dongmian Zou · 2 juin 2026

  Online link recommendation on evolving graphs is performative: by choosing which candidate links to show users, the system changes which links form and what feedback it later observes. Consequently, fairness estimates from logged outcomes can be misleading and may drift after deployment when the rec…

• Grokers: Bottom-Up Inductive Comprehension and Write-Time Intelligence over Typed Knowledge Graphs

  Gregory Magarshak · 2 juin 2026

  We present Grokers, an architecture for building persistent, structured comprehension of typed knowledge graphs through bottom-up inductive traversal of dependency subgraphs. Unlike retrieval-augmented generation (RAG), which pays full comprehension cost at every query, Grokers pushes intelligence t…

• PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning

  Daize Dong, Junlin Chen, Haolong Jia, Jiawei Wu, Huanwei Di, Jiang Liu, Jialian Wu, Zhengzhong Liu, Zicheng Liu, Emad Barsoum, Dimitris N. Metaxas, Hongyi Wang · 2 juin 2026

  Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale. However, reinforcement learning (RL) on MoE-based LLMs often suffers from training instability. A root cause is router drift, i.e., expert activations can change drastically across model updates and differ bet…

• RADE: Random Add-Drop Edge as a Regularizer

  Danial Saber, Amirali Salehi-Abari · 2 juin 2026

  Graph Neural Networks (GNNs) suffer from overfitting and over-squashing of long-range information. Stochastic graph augmentations (e.g., edge deletion) regularize training against overfitting but can introduce train-inference misalignment and do not improve over-squashing. In contrast, rewiring meth…

• Confidence-Adaptive SwiGLU for Mixture-of-Experts

  Shaohua Li, Xiuchao Sui, Xiaobing Sun, Yuhang Wu, Liangli Zhen, Yong Liu, Rick Siow Mong Goh · 2 juin 2026

  SwiGLU has become a standard gated activation in modern Transformer MLPs, yet its gate sharpness -- the smoothness and selectivity of the gating function -- is typically fixed throughout training. In this work, we propose Confidence-Aware SwiGLU ($\kappa$-SwiGLU), a variant of SwiGLU for Mixture-of-…

• Temporal Motif Signatures for Temporal Graph Neural Networks

  Dylan Sandfelder, Mihai Cucuringu, Xiaowen Dong · 2 juin 2026

  Real temporal interaction streams carry predictive structure in short-horizon motif patterns -- repetition, reciprocity, star diversity, triadic flow -- that vanilla temporal graph neural networks (TGNNs) often fail to expose to their edge scorers. We show this concretely on MOOC interaction predict…

• Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generation

  Fang Wan, Jingxiang Qu, Yi Liu · 2 juin 2026

  Bayesian inference provides a principled framework for modeling epistemic uncertainty in neural networks by treating predictions as distributions rather than deterministic values. Meanwhile, diffusion-based models for 3D molecular graph generation operate on fragile geometric structures governed by …

• Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs

  Zichao Yue, Zhiru Zhang · 2 juin 2026

  Pre-propagation graph neural networks (PPGNNs) push all graph-dependent computation into a preprocessing step and train only on the resulting dense hop features, which makes them highly scalable. A puzzle in this regime is that more complex hop aggregators do not reliably outperform simpler ones: on…

• G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs

  Yuhan Wang, Yibo Ding, Yutong Ye, Mufan Zhao, Wenbo Zhang, Ruijie Wang, Jianxin Li · 2 juin 2026

  LLM-as-Aligner has emerged as a prevalent pre-training paradigm for Text-Attributed Graphs(TAGS), aligning graph and text modalities into a shared embedding space via CLIP-style contrastive learning. While effective on individual downstream tasks, we observe severe catastrophic forgetting when such …

• Statistical Testing on Directed Graphs by Surrogate Data Generation

  Chun Hei Michael Chan, Alexandre Cionca, Dimitri Van De Ville · 2 juin 2026

  In recent years, graph signal processing has emerged as a powerful framework at the intersection of signal processing and graph theory, providing tools for the analysis of signals defined on nodes while accounting for their relationships represented by edges. These tools have been successfully appli…

• Convex Distance Operator Transport: A Convex and Geometry-Preserving Formulation

  Junhyoung Chung, Euijong Song, Won Hwa Kim, Gunwoong Park · 2 juin 2026

  We introduce Convex Distance Operator Transport (CDOT), the first convex optimal transport framework that aligns distributions across heterogeneous domains by jointly preserving feature correspondence and intrinsic geometric structure. Specifically, CDOT employs an operator-based regularization that…

• Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors

  Junru Zhou, Cai Zhou, Xiyuan Wang, Pan Li, Muhan Zhang · 2 juin 2026

  A popular way to improve the expressive power of graph neural networks (GNNs) is to use Laplacian eigenvectors as additional node features, since they can serve both as structural identifiers and global coordinates of nodes. Properly handling the orthogonal group symmetry among eigenvectors is cruci…

• Chaining 2-FWL GNNs for Combinatorial Graph Alignment

  Marc Lelarge · 2 juin 2026

  For the combinatorial graph alignment problem (GAP) -- finding the node correspondence that maximizes the number of common edges (nce) between two unlabeled graphs -- properly initialized FAQ remains a strong classical baseline, while existing GNN approaches struggle in the purely structural setting…

• From Graph Retrieval to Schema Realization: Counterfactual Validation for Text-to-SPARQL over Heterogeneous Knowledge Graphs

  Yang Zhao, Chengxiao Dai, Yue Xiu, Dusit Niyato · 2 juin 2026

  Text-to-SPARQL maps natural-language questions to executable SPARQL queries over RDF knowledge graphs. While standard evaluations often fix the target graph in advance, practical knowledge graph question answering (KGQA) may involve heterogeneous graph collections with different schemas, partial ali…

• Modeling Spectral Energy Shifts in Spatio-Temporal Graph Anomaly Detection

  Yilin Liu, Hongchao Zhang, Taylor T. Johnson, Ahmad F. Taha, Meiyi Ma · 2 juin 2026

  Graph anomaly detection methods aim to distinguish anomalous nodes. While prior methods characterize anomalies through increased variation in the spectral energy distributions, they overlook those that result in decreased variation, i.e., camouflaged anomalies that appear normal. We show that this t…

• TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions

  Farzaneh Heidari, Guillaume Rabusseau · 2 juin 2026

  Shapley values are a widely used tool for attributing importance and interactions among input variables in black-box models, but their computation involves a function defined over an exponentially large space of subsets. We propose TN-SHAP-G, a framework that exploits structure in graph-structured i…

• On the Theoretical Limitations of Embedding-based Link Prediction

  Samy Badreddine, Emile van Krieken, Luciano Serafini · 2 juin 2026

  Neural networks often map low-dimensional embeddings to high-dimensional output spaces. Usually, the output layer is linear, which can create a "rank bottleneck" that limits the functions a model can represent. Such bottlenecks are ubiquitous in link prediction models, such as knowledge graph embedd…