The paper introduces Graph Cascades, a mesoscopic rewiring technique that enhances Graph Neural Networks by promoting node pairs with strong multi-hop connections to direct edges, improving performanc…

This paper develops specialized, I/O-aware GPU kernels for common GNN layer types, achieving significant speedups and memory reductions compared to existing frameworks.

The paper proposes a two-stage filter-then-verify framework combining GNNs and ModernBERT to accurately detect complex social engineering attacks in email networks by analyzing both structural pattern…

The paper proposes AlertStar, a hyper-relational knowledge graph completion framework, to improve cyber-attack prediction by incorporating rich flow-level metadata (qualifiers) into path reasoning ove…

The paper introduces a cross-attention Graph Neural Network (CrossAtt) that significantly improves the prediction of drug-drug interaction (DDI) mechanism types, demonstrating that explicit modeling o…

The paper proposes Dual-Scale Retentive Dynamics (DSRD), a unified framework that improves representation learning on dynamic graphs by jointly modeling evolving temporal and structural dependencies.

This paper proposes a scalable topological learning framework for higher-order graph representation by introducing simplified and factored cellular Weisfeiler Leman tests and a novel random walk metho…

The paper proposes a zero-shot multi-label topic classification framework and finds that while knowledge graph augmentation improves performance for smaller language models, it offers diminishing retu…

The paper introduces GraphARC, a new benchmark for abstract reasoning on graph-structured data, demonstrating that current state-of-the-art language models struggle with full graph transformation task…

The paper introduces a typed claim network that models cross-document references by explicitly labeling the stance (e.g., agreement, disagreement) of a citation, significantly improving downstream tas…

This paper analyzes the decoding process of masked diffusion models for graph-to-text generation, finding that structural fine-tuning disrupts natural entity-first generation and proposing a structura…

GJDNet proposes a joint disentanglement framework to enhance the robustness of Graph Neural Networks against adversarial attacks by simultaneously stabilizing node representations and decision boundar…

The paper proposes moving the query instead of the KV-cache during cross-instance attention, demonstrating that this approach is significantly cheaper than moving the cache, especially on modern GPU f…

This paper proposes a joint BERT-GNN architecture to systematically extract entities and relationships from diverse historical texts, achieving superior performance over conventional methods.

This paper introduces GraphSteal, an attack framework demonstrating that Graph RAG systems can leak substantial portions of a hidden knowledge graph by treating them as structural oracles.

The paper analyzes the distinct computational roles of positional versus symbolic attention heads in Transformers, demonstrating that symbolic mechanisms generalize more reliably to longer sequences t…

The paper introduces Graph-Distance Contribution Reward (GDCR) and Step Advantage Policy Optimization (SAPO) to provide fine-grained, step-level credit assignment for agentic search by modeling world…

The paper proposes a semi-relaxed Gromov-Wasserstein objective to estimate the latent connectivity structure of large-scale networks, achieving statistically consistent and efficient recovery of the u…

The paper proposes a graph-constrained approach to scale multi-hop training data by decoupling path discovery from path verbalization, significantly expanding the usable corpus size for LLMs.

The paper introduces Parallax, a scalable and numerically stable parameterized Local Linear Attention mechanism that significantly improves LLM performance and efficiency compared to existing methods…