graph neural networks

Accelerating Mixed Discrete-Continuous Motion Planning via Neural Graphs of Convex Sets

This work replaces the costly convex relaxation step required by nominal GCS with a single forward pass through a Graph Attention Network that predicts a set of highly probable candidate paths through the graph, and generates a lightweight ranking network that orders these candidates by their estimated trajectory cost.

TERE4AI: A Knowledge Graph-Based Tool for Generating EU AI Act Compliant Requirements

Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Sampling

This work presents a scalable end-to-end GNN ranking system for production social graphs, focusing on two design choices that are critical in this setting: multi-hash ID embeddings and temporal neighbor sampling.

Who Should Teach? Confidence-Aware Dual-Teacher Learning for Few-Shot Node Classification on Text-Attributed Graphs

This work proposes CoTeach, a Confidence-aware dual-teacher learning framework that dynamically selects the more reliable teacher for each node, and demonstrates that CoTeach consistently improves few-shot node classification performance while reducing unnecessary LLM utilization and associated monetary costs.

Machine Learning-Enhanced Tabu Search for Tactical Wireless Network Design

The proposed learning-assisted Tabu Search notably reduces computation time while consistently producing higher-quality solutions than the standard algorithm, highlighting the potential of combining machine learning with metaheuristics by leveraging the implicit knowledge embedded in search trajectories.

MolLedger: An Additive Graph Neural Network with Chemically Grounded ADME Attributions

A new graph neural network architecture with built-in meaningful per-atom attributions that produces attributions that are more faithful to chemical properties than other interpretability methods because the auxiliary loss in MolLedger anchors the atom scores to chemical properties.

Converse and Collision-Based Achievability for Node Localization with Hybrid Distance-Spectral Graph Positional Encodings

A hybrid distance-spectral encoding that combines anchor-distance profiles with quantized low-frequency Laplacian-energy coordinates is studied, showing that hybrid encodings better recover syntactic-tree geometry than distance-only or spectral-only baselines.

Exploring multi-answer visual question answering with object detection: a systematic review

This systematic literature review (SLR) focuses on multi answer VQA systems and the use of object detection, following the PRISMA 2020 guidelines and proposes a taxonomy of multi-answer VQA organized along four dimensions.

Rethinking Message Passing as Retrieval for Text-Attributed Graph Learning

This work proposes RTA, a simple MLP-based framework that replaces structural message passing with label-aware retrieval and propagation and provides theoretical insights that connect retrieval-based aggregation to softmax-attention message passing and establish the robustness of retrieved-context supervision to mis-re...

RIDGE: an emulated-network telemetry dataset with trained checkpoints and evaluation outputs for root cause analysis

RIDGE (Residual-Informed Diagnosis from Graph-Structured Evidence) is a two-stage temporal graph neural network architecture for root cause analysis (RCA) in computer networks. A probabilistic emulator forecasts the next telemetry snapshot in a fault-free network. Comparing the observations with that forecast produces...

RIDGE: an emulated-network telemetry dataset with trained checkpoints and evaluation outputs for root cause analysis

RIDGE (Residual-Informed Diagnosis from Graph-Structured Evidence) is a two-stage temporal graph neural network architecture for root cause analysis (RCA) in computer networks. A probabilistic emulator forecasts the next telemetry snapshot in a fault-free network. Comparing the observations with that forecast produces...

The Three Walls of Pattern Recognition: Fundamental Limits and Structured Approximations in Discrete Bayesian Learning

Machine learning is often advanced by scaling models, data, and computation, yet scaling encounters basic limits of learning. A model may require more memory than a machine can provide, more data than can realistically be collected, or a representation that does not match the structure of the problem. These difficultie...