{"total":13,"items":[{"citing_arxiv_id":"2606.24637","ref_index":35,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Application of Deep Learning to Jet Charge Discrimination","primary_cat":"hep-ph","submitted_at":"2026-06-23T14:30:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Graph neural network achieves AUC of 0.883 for up versus anti-up quark jet charge discrimination in controlled QCD simulations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.19623","ref_index":24,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"SEAGAN: domain-Specific and Edge-Aware Graph Attention Network for Dynamic Plant Processes","primary_cat":"cs.LG","submitted_at":"2026-06-17T22:04:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SEAGAN applies a domain-specific graph attention network to classify limitation states in A-Ci curves, achieving F1-score 0.857 and accuracy 0.882 on synthetic data with known ground truth.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30470","ref_index":46,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?","primary_cat":"cs.LG","submitted_at":"2026-05-28T18:41:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The paper demonstrates a black-box model extraction attack on graph classification models that leverages binary subgraph explanations to guide Monte Carlo edge sensitivity estimation with concentration guarantees.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18872","ref_index":61,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"EUPHORIA: Efficient Universal Planning via Hybrid Optimization for Robust Industrial Robotic Assembly","primary_cat":"cs.LG","submitted_at":"2026-05-15T18:25:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"EUPHORIA is a hybrid framework using meta-learning via graph hypernetworks, physics-biased attention in graph transformers, and residual stability correction for few-shot adaptable robotic assembly planning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09226","ref_index":1,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Quantum Injection Pathways for Implicit Graph Neural Networks","primary_cat":"quant-ph","submitted_at":"2026-05-09T23:51:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Independent quantum signal injection into graph DEQs yields higher test accuracy and fewer solver iterations than state-dependent or backbone-dependent injection and classical equilibrium models on NCI1, PROTEINS, and MUTAG benchmarks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"works, implicit neural networks, deep equilibrium models, quan- tum deep equilibrium models, quantum-classical learning, pa- rameterized quantum circuits, graph classification I. INTRODUCTION ANDBACKGROUND A. Graph Neural Networks and Implicit Graph Models Graph neural networks (GNNs) are a leading machine learning framework for graph-structured data in chemistry, biology, and relational reasoning [1], [2]. Common message- passing architectures such as GCN, GraphSAGE, and GIN use explicit finite-depth propagation [3]-[5]; increasing this depth can improve accuracy but often results in growing optimization difficulty [6]. This motivates alternatives that reduce reliance on increasingly deep explicit propagation. Deep equilibrium models (DEQs) offer one such alternative:"},{"citing_arxiv_id":"2605.05476","ref_index":137,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Unified Benchmark for Evaluating Knowledge Graph Construction Methods and Graph Neural Networks","primary_cat":"cs.LG","submitted_at":"2026-05-06T21:53:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A dual-purpose benchmark supplies two text-derived knowledge graphs and one expert reference graph on the same biomedical corpus to jointly measure construction method quality and GNN robustness via semi-supervised node classification.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05463","ref_index":27,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Robustness of Graph Self-Supervised Learning to Real-World Noise: A Case Study on Text-Driven Biomedical Graphs","primary_cat":"cs.LG","submitted_at":"2026-05-06T21:38:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Feature reconstruction in GSSL is robust to noise in text-driven biomedical graphs while relation reconstruction is sensitive, with bidirectional GNN architectures performing better on noisy data and yielding up to 7% gains over language model baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21649","ref_index":118,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion","primary_cat":"cs.AI","submitted_at":"2026-04-23T13:13:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"GS-Quant generates coarse-to-fine discrete codes for KG entities via semantic hierarchy injection and causal sequence reconstruction, enabling LLMs to perform knowledge graph completion by treating the codes as vocabulary tokens.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21094","ref_index":1,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Spectral Embeddings Leak Graph Topology: Theory, Benchmark, and Adaptive Reconstruction","primary_cat":"cs.LG","submitted_at":"2026-04-22T21:31:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LoGraB creates fragmented graph benchmarks with controls for radius, spectral quality, noise, and coverage, while AFR reconstructs faithful graph islands from spectral patches using fidelity scoring, RANSAC-Procrustes alignment, and adaptive stitching, supported by recovery proofs and strong results","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.09922","ref_index":67,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"K-STEMIT: Knowledge-Informed Spatio-Temporal Efficient Multi-Branch Graph Neural Network for Subsurface Stratigraphy Thickness Estimation from Radar Data","primary_cat":"cs.LG","submitted_at":"2026-04-10T21:41:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"K-STEMIT reduces RMSE by 21% for subsurface stratigraphy thickness estimation from radar data via a knowledge-informed spatio-temporal GNN with adaptive feature fusion and physical priors from the MAR weather model.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Overall, this multi-branch design enables the model to leverage both localized spatial structures and temporal dynamics in a complementary manner, leading to more accurate and physically consistent predictions. 4.3. GraphSAGE Inductive Framework GraphSAGE [14] is an inductive GNN framework that generates node embeddings by aggregating information from a node's local neighborhood [67]. In our spatial branch, we apply GraphSAGE to the compressed spatial graph withnodefeaturematrix ̃𝐗spatial ∈ℝ 256×(6𝑚+2),whereeachnodecorrespondstoafixedlocationacrosslayersandhas concatenated feature vectors derived from all top𝑚internal layers. Let ̃𝐱(𝑣) ∈ℝ 6𝑚+2 denotetheinputfeatureofnode𝑣in ̃𝐗spatial,andlet(𝑣)denoteitsneighborhood.GraphSAGE updates the node representation as follows:"},{"citing_arxiv_id":"2501.05614","ref_index":6,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Watermarking Graph Neural Networks via Explanations for Ownership Protection","primary_cat":"cs.CR","submitted_at":"2025-01-09T23:25:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Explanation-based watermarking for GNNs creates statistically distinct explanations for ownership verification, with a proof that locating the watermark is NP-hard even with full method knowledge.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2407.07639","ref_index":101,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Explaining Graph Neural Networks for Node Similarity on Graphs","primary_cat":"cs.LG","submitted_at":"2024-07-10T13:20:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Empirical comparison shows gradient-based explanations for GNN node similarities are actionable, consistent, and retain effects when sparsified, unlike mutual information explanations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2403.18136","ref_index":50,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics","primary_cat":"cs.LG","submitted_at":"2024-03-26T22:41:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"An explanation-based detector using seven novel metrics derived from GNN explanations identifies backdoored graphs with high performance on benchmark datasets against multiple attack models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}