← Home

Daily arXiv Papers

Graph Neural Networks · Graph Learning · LLM × Graph

Showing 17 papers for 2026-02-16

Coden: Efficient Temporal Graph Neural Networks for Continuous Prediction
GNN Graph Learning

Coden proposes efficient temporal graph neural networks for continuous prediction, addressing the need for frequent predictions over time rather than a single forecast over a fixed temporal window. It analyzes the computational bottlenecks of adapting TGNNs to continuous inference on large graphs and presents design choices to balance runtime with prediction quality.

Which Algorithms Can Graph Neural Networks Learn?
GNN Graph Learning

The paper investigates what discrete algorithms graph neural networks can learn, in the area of neural algorithmic reasoning. It examines the capabilities and limitations of MP-GNNs for algorithm execution and discusses the lack of formal guarantees in many empirical studies, aiming to characterize learnable classes of algorithms.

FlashSchNet: Fast and Accurate Coarse-Grained Neural Network Molecular Dynamics
GNN Graph Learning

FlashSchNet introduces an IO-aware GNN-MD framework that optimizes data movement between GPU high-bandwidth memory and on-chip SRAM to accelerate molecular dynamics simulations. It achieves faster and more accurate SchNet-style potentials by accounting for IO bottlenecks.

Learning to Approximate Uniform Facility Location via Graph Neural Networks
GNN Graph Learning

The work explores using graph neural networks to approximate the Uniform Facility Location problem, aiming to provide fast heuristics with performance guarantees inspired by classical approximation algorithms. It discusses training and architectural choices to achieve competitive performance without relying on heavy supervised data or reinforcement learning.

VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
GNN Graph Learning

VDW-GNNs introduce vector diffusion wavelets for geometric GNNs, enabling wavelet-based processing on data lying in tangent bundles. The framework is evaluated on synthetic point clouds and real-world data such as wind fields and neural activity, with theoretical insights into the method.

What Do Temporal Graph Learning Models Learn?
GNN Graph Learning

The paper asks what temporal graph learning models actually learn, examining reliability of benchmarks and the risk of simple heuristics competing with state-of-the-art. It analyzes which graph properties and dynamics models leverage to make predictions.

ATLAS: Adaptive Topology-based Learning at Scale for Homophilic and Heterophilic Graphs
GNN Graph Learning

ATLAS is a propagation-free framework for learning on graphs that handles both homophilic and heterophilic settings by encoding topology via multi-resolution community features rather than message passing. The paper proves a fundamental trade-off in community refinement between granularity and performance and demonstrates scalability.

Bayesian Neighborhood Adaptation for Graph Neural Networks
GNN Graph Learning

Bayesian Neighborhood Adaptation for GNNs proposes a Bayesian approach to adaptively select neighborhood scope for aggregation, avoiding exhaustive search over fixed hops. It aims to improve robustness across homophilic and heterophilic graphs.

SaVe-TAG: LLM-based Interpolation for Long-Tailed Text-Attributed Graphs
LLM × Graph Graph Learning

SaVe-TAG uses LLM-based semantic interpolation for long-tailed text-attributed graphs via semantic-aware vicinal risk minimization, going beyond embedding arithmetic. It preserves rich textual semantics and improves generalization across head and tail classes.

Bayesian Ego-graph Inference for Networked Multi-Agent Reinforcement Learning
Graph Learning

Bayesian Ego-graph Inference for Networked-MARL introduces a stochastic ego-graph policy to capture local graph uncertainty and enable dynamic neighborhood adaptation in decentralized multi-agent reinforcement learning. It improves robustness and coordination under changing network conditions.

TA-KAND: Two-stage Attention Triple Enhancement and U-KAN based Diffusion For Few-shot Knowledge Graph Completion
Knowledge Graph Graph Learning

TA-KAND presents a two-stage attention-based triple enhancement and diffusion method (U-KAN based) for few-shot KG completion, addressing long-tailed relation distributions. It improves how few-shot relations are inferred by refining relation triples and diffusing information.

Evolving Beyond Snapshots: Harmonizing Structure and Sequence via Entity State Tuning for Temporal Knowledge Graph Forecasting
Knowledge Graph Graph Learning

Entity State Tuning (EST) is an encoder-agnostic framework for temporal knowledge graph forecasting that endows forecasters with persistent and evolving entity states, addressing episodic amnesia and long-term dependency decay. It integrates structure and sequence for better predictions.

Intent-Driven Smart Manufacturing Integrating Knowledge Graphs and Large Language Models
Knowledge Graph LLM × Graph

Intent-Driven Smart Manufacturing integrates instruction-tuned LLMs with ontology-aligned knowledge graphs to translate human intents into machine-executable requirements. The paper demonstrates fine-tuning Mistral-7B-Instruct-V02 to generate structured JSON requirement models from natural language.

WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning
Graph Learning

WebClipper compresses web agent trajectories by graph-based pruning, removing unproductive branches in the agent's state graph to speed up search without sacrificing results.

Beyond Static Question Banks: Dynamic Knowledge Expansion via LLM-Automated Graph Construction and Adaptive Generation
Knowledge Graph Graph Learning LLM × Graph

Beyond Static Question Banks proposes dynamic knowledge expansion via LLM-automated graph construction and adaptive generation for personalized education. It addresses cost and scalability by automating KG creation and state-aware reasoning rather than relying on static question banks.

Semantic Communities and Boundary-Spanning Lyrics in K-pop: A Graph-Based Unsupervised Analysis
Graph Theory Graph Learning

Semantic Communities and Boundary-Spanning Lyrics in K-pop presents a graph-based unsupervised analysis of K-pop lyrics to discover semantic communities across multilingual and repetitive content. The framework constructs line-level semantic representations and detects topic-level communities.

RLMiner: Finding the Most Frequent k-sized Subgraph via Reinforcement Learning
Graph Theory Graph Learning

RLMiner frames the problem of finding the most frequent induced subgraph of size k as a reinforcement learning task, aiming to overcome NP-hard counting cost. It proposes an RL-based search strategy that reduces enumeration time and scales to larger graphs.