Advanced Graph Neural Networks

Derniers papiers

• EO-Agents: A Three-Agent LLM Pipeline for Earth Observation Hypothesis Generation

  Mahyar Ghazanfari, Amin Tabrizian, Armin Mehrabian, Peng Wei · 3 juillet 2026

  Large language models have recently been explored for scientific hypothesis generation, but most prior work relies on unstructured literature and free-form textual claims. We present a pipeline for Earth observation that grounds hypothesis generation directly in the NASA Earth Observation Knowledge …

• Bringing Agentic Search to Earth Observation Data Discovery

  Minghan Yu, Youran Sun, Chugang Yi, Yixin Wen, Haizhao Yang · 3 juillet 2026

  NASA and its data centers hold thousands of geoscience datasets and tools like Worldview, Giovanni, the Science Discovery Engine, and Harmony. Finding the right one is hard even for domain experts. We present an agentic search system, deployed as a public service for the geoscience community, that t…

• IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs

  Samir Abdaljalil, Erchin Serpedin, Hasan Kurban · 3 juillet 2026

  We introduce ISOSCI, a benchmark of isomorphic cross-domain science problem pairs that separates reasoning ability from domain knowledge retrieval in LLM evaluation. Each pair shares identical logical structure but requires different domain-specific knowledge, enabling controlled attribution of reas…

• Geometry as a Missing Axis of Representation Quality: The Variational Geometric Information Bottleneck under Data Scarcity

  Ronald Katende · 3 juillet 2026

  We study latent geometry as an explicit component of representation quality in data-scarce learning. For an encoder (\phi), we define (Q_{\beta,\gamma}(\phi)=I(\phi(X);Y)-\beta\mathcal C(\phi)-\gamma d_{\mathrm{int}}(\phi)), combining task-relevant information with penalties for curvature and intrin…

• Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization

  Jan Drchal · 3 juillet 2026

  Large language models (LLMs) are often asked to produce JSON conforming to a fixed schema, powering information extraction, tool calling, agentic planning, and knowledge-graph construction. Measuring how closely an output matches a gold reference is essential yet surprisingly hard: exact match is br…

• Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space

  Di Wu, Huan Liu, Zhixiang Chi, Yuanhao Yu, Konstantinos N. Plataniotis, Yang Wang · 3 juillet 2026

  The rapid advancements in using neural networks as implicit data representations have attracted significant interest in developing machine learning methods that analyze and process the weight spaces of other neural networks. However, efficiently handling these highdimensional weight spaces remains c…

• X-LogSMask: Expand Transformer for Graph-Structured Data

  Leyan Li, Rennong Yang, Zhenxing Zhang, Liping Hu · 3 juillet 2026

  Transformers have become general-purpose architectures, but their all-to-all self-attention is poorly matched to graph data, whose interactions are sparse, structured and multi-scale. Existing Graph Transformers address this mismatch through structural encodings, hybrid message-passing modules or le…

• Embedding Inference Attack

  Cedric Fitiavana Raelijohn, S\'ebastien Gambs, Jean-Francois Rajotte · 3 juillet 2026

  Embedding models are essential components of modern Information Retrieval (IR) systems, yet they are typically hidden behind APIs. Recent works have shown that dense IR system can lead to security vulnerabilities such as embedding inversion attacks. However, such attacks usually require that the att…

• CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models

  Qizhi Jiang, Shuo Wang, Pei Ke, Yuhang Song, Ke Qin · 2 juillet 2026

  Large Reasoning Models (LRMs) have achieved remarkable success on complex tasks by leveraging long chain-of-thought (CoT) trajectories, yet they frequently exhibit overthinking on simple queries, resulting in significant token overhead and reduced inference efficiency. However, existing compression …

• AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation

  Bao Long Nguyen Huu, Atsushi Hashimoto · 2 juillet 2026

  GraphRAG is an extension of retrieval-augmented generation (RAG) that supports large language models (LLMs) by referring to graph-structured data as external knowledge. While this technique ideally captures intricate relationships, it often struggles with graph representations for LLMs, particularly…

• Amortized Maximum Inner Product Search with Learned Support Functions

  Theo X. Olausson, Jo\~ao Monteiro, Michal Klein, Marco Cuturi · 2 juillet 2026

  Maximum inner product search (MIPS) is a crucial subroutine in machine learning, requiring the identification of a vector taken within a database (the keys) that best aligns with a given query. We propose amortized MIPS: a regression-based approach that trains neural networks to directly predict MIP…

• SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport

  Yuting Zhang, Yanbei Liu, Zhitao Xiao, Lei Geng, Yanwei Pang, Xiao Wang · 2 juillet 2026

  Self-supervised Continual Graph Learning (CGL) aims to successively learn from a graph sequence with different tasks without label supervision - a paradigm that has attracted widespread attention. Most existing self-supervised CGL methods rely on instance-level consistency objectives that enforce st…

• Relevance Is Not Permission: Warranted Attention for Value Contributions

  Minwoo Yu, Young-guk Ha · 2 juillet 2026

  Relevance is not permission. Attention lets a model read key-value items related to the current query, but it does not guarantee that the value contribution of such an item becomes prediction evidence. A retrieved passage may be relevant to a question without being supporting evidence, and a histori…

• Multi-Label Node Classification with Label Influence Propagation

  Yifei Sun, Zemin Liu, Bryan Hooi, Yang Yang, Rizal Fathony, Jia Chen, Bingsheng He · 2 juillet 2026

  Graphs are a complex and versatile data structure used across various domains, with possibly multi-label nodes playing a particularly crucial role. Examples include proteins in PPI networks with multiple functions and users in social or e-commerce networks exhibiting diverse interests. Tackling mult…

• Beyond Triplet Plausibility: Relation Set Completion in Knowledge Graphs

  Zihao Zheng, Borui Cai, Yao Zhao, Keshav Sood, Yong Xiang · 1 juillet 2026

  Knowledge graphs (KGs) organize real-world knowledge as triplets and underpin many downstream applications. Due to their inherent incompleteness, knowledge graph completion (KGC) is widely studied and is typically formulated as triplet prediction, with link prediction as the dominant paradigm. Howev…

• Nazrin: An Atomic Neural Proof Automation Tactic in Lean 4

  Leni Aniva, Iori Oikawa, David Dill, Clark Barrett · 1 juillet 2026

  In Machine-Assisted Theorem Proving, a theorem proving agent searches for a sequence of expressions and tactics that can prove a statement in a proof assistant. In this work, we introduce several novel concepts and capabilities to address obstacles faced by machine-assisted theorem proving. We first…

• FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning

  Zekai Chen, Kairui Yang, Xuaner Chen, Xunkai Li, Xun Wu, Rong-Hua Li, Guoren Wang · 1 juillet 2026

  Multimodal graph foundation models aim to learn reusable knowledge from graphs enriched with text, images, attributes, and relational topology, thereby supporting diverse graph-centric and modality-centric tasks. In practice, however, such multimodal graphs are often distributed across decentralized…

• Measuring Graph-to-Graph Semantic Similarity in Knowledge Graphs: An Empirical Evaluation of Knowledge Graph Embeddings

  Seungryeol Baek, Wooseok Sim, Hogun Park · 1 juillet 2026

  A Knowledge Graph (KG) represents facts as structured triples and is widely used to organize relational knowledge across diverse domains. Just as textual information ranges from words and sentences to complete documents, KG information can be interpreted at multiple levels, from entities, relations,…

• Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs

  Seyed Alireza Molavi, Zhan Su, Yan Hu, Peyman Sheikholharam Mashhadi, Stefan Byttner, Prayag Tiwari · 1 juillet 2026

  Composing independently trained LoRA adapters into a single large language model is useful for multi-domain adaptation, especially when the original training data cannot be shared. A common approach is to use MoE-style routing over LoRA experts, but for frozen pretrained adapters, soft weighted comb…

• TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learning

  Lingjie Chen, Yuanchen Bei, Haobo Xu, Yanjun Zhao, Yuzhong Chen, Hanghang Tong · 1 juillet 2026

  Text-attributed graphs (TAGs), where each node carries a natural language description, require models to jointly reason over text and graph topology. Existing approaches often handle the two modalities separately: graph neural networks operate on shallow text features, while hybrids of LLMs and grap…

• ComplianceGate: Classifier-Gated Multi-Tier LLM Routing for Inference in Regulated Industries

  Abhishek Dey · 1 juillet 2026

  Large language models deployed in regulated industries operate under two constraints: compliance enforcement and cost efficiency. Personally identifiable information (PII) in user queries can reach model endpoints before the system determines whether that data should leave its jurisdictional boundar…

• The Impact of Dimensionality on the Stability of Node Embeddings

  Tobias Schumacher, Simon Reichelt, Markus Strohmaier · 1 juillet 2026

  Previous work has shown that node embedding methods can produce different representations and downstream predictions across repeated training runs, even when trained on the same data with identical hyperparameters. However, the role of embedding dimensionality in this instability remains poorly unde…

• Curvature-Guided Sheaf Diffusion for Unsupervised Community Detection on Heterophilic Graphs

  Feifan Wang · 30 juin 2026

  Detecting communities in heterophilic graphs -- where connected nodes often belong to different classes -- is hard for unsupervised methods: classical modularity and spectral methods are feature agnostic, while deep graph-clustering methods rely on contrastive or generative machinery that is opaque.…

• KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models

  Boshko Koloski, Xiangjian Jiang, Senja Pollak, Bla\v{z} \v{S}krlj, Mateja Jamnik, Nikola Simidjievski · 30 juin 2026

  Tabular foundation models have advanced deep learning for tabular data by delivering strong default performance across many small and medium tasks. Yet in niche domains, where data is scarce, high-dimensional, and shifted from the pretraining distribution, they may still fail to outperform carefully…

• Rethinking Generative Reconstruction Attacks against Graph Neural Network Models

  Adebayo Keji, Sayanton Dibbo · 30 juin 2026

  The application of graph data in numerous disciplines raises the need for gathering and analyzing huge volumes of data, some of which is private and sensitive. The non-Euclidean nature of the graph data makes the analysis computationally challenging, leading to the use of Graph Neural Networks (GNNs…