Graph Convolutional Memory using Topological Priors

2021-06-27 · Steven D. Morad, Stephan Liwicki, Ryan Kortvelesy, Roberto Mecca, Amanda Prorok

Solving partially-observable Markov decision processes (POMDPs) is critical when applying reinforcement learning to real-world problems, where agents have an incomplete view of the world. We present graph convolutional memory (GCM), the first hybrid memory model for solving POMDPs using reinforcement learning. GCM uses either human-defined or data-driven topological priors to form graph neighborhoods, combining them into a larger network topology using dynamic programming. We query the graph using graph convolution, coalescing relevant memories into a context-dependent belief. When used without human priors, GCM performs similarly to state-of-the-art methods. When used with human priors, GCM outperforms these methods on control, memorization, and navigation tasks while using significantly fewer parameters.

📄 PDF Abstract BibTeX arXiv:2106.14117

Code (1)

smorad/graph-conv-memory 공식 구현 pytorch

Tasks

Memorization reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Non-convolutional Graph Neural Networks

2024-07-31 · Yuanqing Wang, Kyunghyun Cho

Rethink convolution-based graph neural networks (GNN) -- they characteristically suffer from limited expressiveness, over-smoothing, and over-squashing, and require specialized sparse kernels for efficient computation. H…

Graph Learning

EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation

2026-06-02 · Zuhao Ge, Xiaosong Jia, Chao Wu, Yuchen Zhou 외 arxiv

Building memory is essential for long-horizon planning in zero-shot embodied navigation. Detector-centric scene graphs often compress observations into sparse nodes, discarding fine-grained visual evidence and accumulati…

Zero-shot Generalization 3D Reconstruction

Graph-Augmented Topological Internalization with Dual-Stream Classifiers for Medical Report Generation

2026-05-04 · Moyu Tang, Chupei Tang, Junxiao Kong, Di Wang 외 arxiv

Automated medical report generation, MRG, holds substantial value for alleviating radiologist workload and enhancing diagnostic efficiency. However, mainstream approaches typically treat diverse chest abnormalities as is…

Medical Report Generation Zero-shot Generalization Visual Grounding

Pose Invariant Topological Memory for Visual Navigation

2021-01-01 · ICCV 2021 10 · Asuto Taniguchi, Fumihiro Sasaki, Ryota Yamashina

Planning for visual navigation using topological memory, a memory graph consisting of nodes and edges, has been recently well-studied. The nodes correspond to past observations of a robot, and the edges represent the…

Contrastive Learning Data Augmentation Visual Navigation

Stock Price Prediction Using Temporal Graph Model with Value Chain Data

2023-03-07 · Chang Liu, Sandra Paterlini

Stock price prediction is a crucial element in financial trading as it allows traders to make informed decisions about buying, selling, and holding stocks. Accurate predictions of future stock prices can help traders opt…

Stock Price Prediction