Explore learning and reasoning over graphs, including graph neural networks and knowledge graphs. Compare methods for relational and structured data.
32 papers · Latest edition October 5, 2026
Three of the latest briefs in this collection. Read the evidence and the original papers alongside them.
CodeGraph turns 167 million source files into a Wikidata-grounded knowledge graph of algorithms, paradigms, patterns, and software domains.
GraphWrit3R turns 3D spatial data into open-vocabulary scene graphs using multimodal encoders and an LLM, without requiring ground-truth object annotations at inference.
This work shows how a small, carefully designed set of single-variable interventions can recover causal structure even when hidden confounders and selection bias complicate the data.
Newest editions first.
Federico Pennino, Andrea Gurioli, Stefano Zacchiroli, Maurizio Gabbrielli, Paolo Ferragina
CodeGraph turns 167 million source files into a Wikidata-grounded knowledge graph of algorithms, paradigms, patterns, and software domains.
Luka Milivojevic, Nikola Popovic, Sayan Deb Sarkar, Sebastian Koch, Iro Armeni, Luc Van Gool, Danda Pani Paudel
GraphWrit3R turns 3D spatial data into open-vocabulary scene graphs using multimodal encoders and an LLM, without requiring ground-truth object annotations at inference.
Xiaotian Hou, Kwangmoon Park, Hongzhe Li
This work shows how a small, carefully designed set of single-variable interventions can recover causal structure even when hidden confounders and selection bias complicate the data.
Runhao Jiang, Renchi Yang
This paper makes massive-scale item recommendations much faster by approximating graph-based similarity scores without sacrificing retrieval quality.
Fabricio Breve
This work uses particle-based graph dynamics to clean noisy labels before training GCNs, improving robustness while keeping computation low.
Maëlic Neau
RelateAnything aims to make scene-graph relation prediction as flexible as open-vocabulary detection by predicting arbitrary text-specified relations in real time.
Dac Duy Anh Nguyen, Zhangchi Qiu, Shigeng Chen, Alan Wee-Chung Liew
A timely survey explains how graph-structured memories can help LLM agents remember, update, and retrieve personalized information over long-term interactions.
Lintai Hou
Graph Machine replaces much of a Transformer with dynamically routed pointer-like edges, achieving near-preserved language-modeling quality while retrieving only a few tokens per head.
Furqan Nasir, Muhammad Atif Saeed, Muhammad Ehsan, Sher Jeel Ahmad, Abdul Moiz Altaf
OntoKG-EQ turns emerging-market financial analysis into reproducible, provenance-linked answers that can be checked from the final claim back to the original evidence.
Yilun Liu, Boyu Luo, Yanran Tang, Ruihong Qiu, Zi Huang
CNY teaches language models to choose which graph neighbours to inspect while reasoning, rather than forcing them to rely on a fixed context.
Xiaoyu Guo, Pengcheng Chen, Jiong Yu, Yi Lu, Yaohua Wang, Ziyang Li
The paper shows that feeding graphs to an LLM is not enough—the graph must be presented in a form the decoder can actually use.
Xinjian Zhao, Wei Pang, Zhixuan Yu, Xiangru Jian, Xiaozhuang Song, Yaoyao Xu, Zhongkai Xue, Dingshuo Chen, Shu Wu, Philip Torr, Tianshu Yu
This survey explores how AI can combine the structure of graphs with the visual intuition humans use to understand them.
Zichun Jin, Zihan Zhou, Yinan Liu, Bin Wang, Xiaochun Yang
AdaptedKG uses calibrated knowledge-graph clues to identify and downweight misleading user interactions before they distort sequential recommendation.
Rong-Hua Li, Meihao Liao, Yichun Yang
This paper shows that estimating a graph’s spectral structure is exponentially hard classically but can become polynomially efficient with quantum access.
Noah Dahle, Anne Tumlin, Ngoc Tran, Xenofon Koutsoukos, Tyler Derr
RAD detects unusual behavior in multi-table databases by combining graph-based learning with human-readable behavioral rules.
Youngseok Song, Sofia C. Olhede
This paper improves the estimation of multiple sparse networks by letting information from one interaction layer sharpen the analysis of the others.
Steve Brown
Quipu is a knowledge-graph store designed to ensure that agent-written facts are admitted, trusted, time-stamped, and auditable by construction.
Sai Karthik Navuluru, Siddhartha Shankar Das, Bo Ni, Hongjie Chen, Yu Wang, Baris Coskunuzer, Nesreen K. Ahmed, Franck Dernoncourt, Mahantesh Halappanavar, Tyler Derr, Ryan A. Rossi, Lakshman Tamil
This paper gives graph neural networks a common architectural language for understanding, comparing, and designing many different layers.
Maya Arseven, Anette Frank, Beni Egressy, Johann Higl, Moritz Plenz
GLM-RAG shows that graph language models can make knowledge-graph retrieval more transferable for multi-hop question answering than conventional alternatives.
Seyed Alireza Hosseini
The paper proves that an apparently powerful unrolled graph denoiser can only realize a narrow class of polynomial graph filters, limiting its expressive power and practical accuracy.
Chen Shao, Yue Wang, Zhenyi Zhu, Zhanbo Huang, Tobias Käfer, Zonghan Wu, Danai Koutra
This work shows why graph-based time-series models break when correlations shift over time and proposes GLIDE to make them more robust.
Aaron Feller, Kris Deibler, Maxim Secor
A pretrained geometric model that treats cyclic peptides as conformational ensembles improves property prediction over sequence-only modeling.
Rachid Caich, Yassine Abbahaddou
This work uses global geometric curvature to explain and improve how information flows through graph neural networks.
Tianpeng Li, Xuan Guo, Wenjun Wang, Wang Zhang, Pengfei Jiao
Temporal graph generators cannot reliably correct deployment drift from observations alone, because unseen structural changes create an irreducible error floor.
Mikhail Komarov, Ivan Bondarenko, Stanislav Shtuka, Oleg Sedukhin, Roman Shuvalov, Yana Dementyeva, Matvey Solovyov, Nikolay O. Nikitin
RAGU builds cleaner knowledge graphs with a compact language model, making GraphRAG more accurate, efficient, and practical.
Sepehr Assadi, Max Jiang, Mars Xiang
After two decades, this paper proves that in severely memory-limited streaming matching, simple greedy is as good as any possible algorithm.
Bao Long Nguyen Huu, Atsushi Hashimoto
AGE improves GraphRAG by learning which graph nodes to mask during self-supervised training, making graph embeddings better aligned with frozen LLMs for graph question answering.
Philip Zucker
This paper introduces a new way to handle variables inside e-graphs so algebraic rewrites can be done more safely and elegantly.
Subhadeep Pal, Shashwat Sourav, Tirthankar Ghosal, Markus J. Buehler
This paper trains AI to reason like a graph-builder, turning scientific questions into traceable chains of concepts that help generate better hypotheses for materials discovery.
Shuofei Qiao, Yunxiang Wei, Jiazheng Fan, Bin Wu, Busheng Zhang, Mengru Wang, Yuqi Zhu, Ningyu Zhang, Keyan Ding, Qiang Zhang, Huajun Chen
SciAtlas builds a massive cross-disciplinary knowledge graph for science and pairs it with graph-based retrieval to help AI agents do better literature search, synthesis, and research planning.
Ding Zhang, Runtao Zhou, Wenqing Zheng, Rizal Fathony, Bayan Bruss, Chirag Agarwal
This paper shows that the most salient graph tokens in graph language models are not actually the ones carrying the important graph information, revealing a hidden mismatch in how these models represent graphs.
Yunhua Pei, Zixing Song, Jin Zheng, John Cartlidge
This paper improves unsupervised anomaly detection in multivariate time series by using dynamic graph contrastive learning to model changing relationships instead of forcing them to stay fixed.