We present RL-VAE, a graph-to-graph variational autoencoder that uses reinforcement learning to decode molecular graphs from latent embeddings. Methods have been described previously for graph-to-graph autoencoding, but these approaches require sophisticated decoders that increase the complexity of training and evaluat…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “graph reinforcement learning”
Graph Cascades rewire graphs to improve structure-aware learning.
problem Improving graph neural networks and transformers for structure-aware learning.
method Graph Cascades uses contagion-based diffusion processes to construct an auxiliary graph with reinforced edges.
result Graph Cascades improves node-classification benchmarks across various graph types.
Reinforcement learning (RL) tasks are challenging to implement, execute and test due to algorithmic instability, hyper-parameter sensitivity, and heterogeneous distributed communication patterns. We argue for the separation of logical component composition, backend graph definition, and distributed execution. To this e…
KGRL uses reinforcement learning with knowledge graphs for better interactive recommendation.
problem Achieving responsiveness and accuracy in dynamic user-item interactions.
method KGRL combines reinforcement learning and knowledge graphs, using a local knowledge network and attention mechanism.
result KGRL outperforms state-of-the-art methods in simulated and real-world environments.
AI learns to design chemical processes efficiently.
problem Designing efficient chemical processes.
method Hierarchical reinforcement learning and graph neural networks.
result Quick learning in various decision spaces.
Study of reinforcement learning with additional feedback observations.
problem Episodic reinforcement learning in Markov decision processes with feedback observations.
method Formalization of feedback graph, model-based algorithms leveraging feedback, regret bound analysis.
result Regret bound depends only on the size of the maximum acyclic subgraph of the feedback graph.
Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawingcs.LG
New method learns high-quality Laplacian representations for reinforcement learning.
problem Lack of accurate Laplacian representations in large or continuous state spaces.
method Reformulated spectral graph drawing objective to have eigenvectors as unique global minimizer.
result Learned Laplacian representations more faithfully approximate the ground truth.
New method tackles parcel routing with AI.
problem Routing parcels efficiently through a network of hubs.
method Combines graph neural networks with model-free RL.
result Extracts small feature graphs from the environment state.
Improved RL for knowledge graph reasoning with entity types.
problem Challenges in path-based relational reasoning over knowledge graphs.
method Type-enhanced RL agent using GNN for neighborhood information.
result Outperforms state-of-the-art RL methods and discovers novel paths.
Linear-time graph optimization using reinforcement learning.
problem Solving combinatorial optimization problems on real-world graphs.
method Graph neural network trained with reinforcement learning.
result Approximate solutions in linear time for various graph problems.
We present a deep reinforcement learning approach to minimizing the execution cost of neural network computation graphs in an optimizing compiler. Unlike earlier learning-based works that require training the optimizer on the same graph to be optimized, we propose a learning approach that trains an optimizer offline an…
Graph Neural Networks (GNNs) have been popularly used for analyzing non-Euclidean data such as social network data and biological data. Despite their success, the design of graph neural networks requires a lot of manual work and domain knowledge. In this paper, we propose a Graph Neural Architecture Search method (Grap…
Graph neural network executes value iteration for flexible environments.
problem Value iteration in flexible environments with direct supervision.
method Graph Neural Network (GNN) executing value iteration algorithm.
result GNN accurately models value iteration across diverse environments.
Deep Graph Convolutional Reinforcement Learning for Financial Portfolio Management -- DeepPocketq-fin.CP
DeepPocket uses graph convolutional reinforcement learning for better financial portfolio management.
problem Maximizing return on investment while managing risk in correlated financial assets.
method Graph convolutional reinforcement learning framework with feature extraction, local information collection, and actor-critic reinforcement learning.
result DeepPocket outperformed market indexes on five real-life datasets over three investment periods, including during the Covid-19 crisis.
Graph Neural Networks solve topology problems in simple 3D models.
problem Deciding homeomorphism of 3-manifolds described by plumbing graphs.
method Supervised and reinforcement learning with Graph Neural Networks.
result High accuracy in determining homeomorphic 3-manifolds.
Paper tackles active learning for GNNs, reducing annotation costs.
problem Efficiently label nodes on graphs to reduce GNN training costs.
method Formulates as a sequential decision process, trains GNN-based policy network with reinforcement learning.
result Trains a transferable active learning policy that generalizes across different domains.
TOMA generates abstract graphs for RL, reducing memory and computation costs.
problem High memory and computation costs in graph generation for RL.
method Topological Map Abstraction (TOMA) for generating abstract graphs.
result TOMA reduces memory and computation costs compared to existing methods.
IG-RL learns adaptive traffic signals for any network, outperforming existing methods.
problem Adaptive traffic signal control for large networks with combinatorial state and action spaces.
method Graph-Convolutional Networks for decentralized, flexible control.
result IG-RL generalizes to new networks and traffic conditions without additional training.
Method integrates logical rules into neural multi-hop reasoning for drug repurposing.
problem Capturing long-range dependencies in biomedical data.
method Combines logical rules with neural multi-hop reasoning using reinforcement learning.
result Our method outperforms baseline methods in drug repurposing tasks.
A novel method for visual question answering using scene graphs and reinforcement learning.
problem Answering free-form questions about images with deep linguistic and visual understanding.
method Context-driven, sequential reasoning based on scene graphs and reinforcement learning.
result Our method almost reaches human performance on the GQA dataset.
New method shows ignoring morphological graph info improves reinforcement learning performance.
problem Improving reinforcement learning performance in incompatible environments.
method Transformer-based approach (Amorpheus) that ignores morphological graph information.
result Transformer-based approach outperforms GNN-based methods that use morphological information.
Learning to cooperate is crucially important in multi-agent environments. The key is to understand the mutual interplay between agents. However, multi-agent environments are highly dynamic, where agents keep moving and their neighbors change quickly. This makes it hard to learn abstract representations of mutual interp…
Deep RL learns effective job shop scheduling rules from raw features.
problem Designing effective priority dispatching rules for job shop scheduling is challenging.
method End-to-end deep reinforcement learning using Graph Neural Networks.
result Agent learns high-quality dispatching rules from raw features and generalizes well to unseen instances.
GraphOpt learns the formation mechanism of graphs from observed structures.
problem Learning formation mechanisms from observed graphs with complex structural properties.
method GraphOpt uses maximum entropy inverse reinforcement learning to solve the link formation problem in a sequential decision-making process.
result GraphOpt discovers a latent objective function that can explain and transfer across different graphs.
Proposes active learning for meta-learning in graph node response prediction.
problem Difficulty in improving performance with meta-learning due to unbalanced observations.
method Combines graph convolutional neural networks and reinforcement learning for both prediction and node selection.
result Can predict responses and select nodes even for unseen response variables.
In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation policy iteration (RPI). We consider the limitations of proto-value functions (PVFs) at accurately approximating the value function in low d…
New RL approach builds short ancestral recombination graphs.
problem Building short ancestral recombination graphs (ARGs).
method Reinforcement Learning applied to genetic sequences.
result RL can build ARGs as short as heuristic algorithms.
We present a method to generate directed acyclic graphs (DAGs) using deep reinforcement learning, specifically deep Q-learning. Generating graphs with specified structures is an important and challenging task in various application fields, however most current graph generation methods produce graphs with undirected edg…
Stochastic computation graphs (SCGs) provide a formalism to represent structured optimization problems arising in artificial intelligence, including supervised, unsupervised, and reinforcement learning. Previous work has shown that an unbiased estimator of the gradient of the expected loss of SCGs can be derived from a…
G1 uses RL to enhance LLMs' graph reasoning, improving performance on diverse tasks.
problem Limited graph reasoning abilities of LLMs, especially in synthetic graph-theoretic tasks.
method Curated synthetic graph dataset, RL training on LLMs.
result Significant improvements in graph reasoning, zero-shot generalization to unseen tasks.
Proves error bounds for state representation in RL using graph spectral features.
problem Addressing the curse of dimensionality in RL with unknown transition graphs.
method Proves upper bounds on approximation error of linear value function approximation using learned spectral features of the state-graph.
result Error bounds scale with algebraic connectivity and eigenvector estimation error.
Graphs can be used to represent and reason about systems and a variety of metrics have been devised to quantify their global characteristics. However, little is currently known about how to construct a graph or improve an existing one given a target objective. In this work, we formulate the construction of a graph as a…
Similarity graphs are an active research direction for the nearest neighbor search (NNS) problem. New algorithms for similarity graph construction are continuously being proposed and analyzed by both theoreticians and practitioners. However, existing construction algorithms are mostly based on heuristics and do not exp…
Real-world graph applications, such as advertisements and product recommendations make profits based on accurately classify the label of the nodes. However, in such scenarios, there are high incentives for the adversaries to attack such graph to reduce the node classification performance. Previous work on graph adversa…
A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learningcs.LG
This paper considers a distributed reinforcement learning problem in which a network of multiple agents aim to cooperatively maximize the globally averaged return through communication with only local neighbors. A randomized communication-efficient multi-agent actor-critic algorithm is proposed for possibly unidirectio…
GNN-CL model improves financial fraud detection using graph neural networks and reinforcement learning.
problem Complex financial fraud detection with high false positive rates.
method Combines GNN, CNN, LSTM, and MLPS to analyze transaction patterns and uses reinforcement learning to filter out noise.
result GNN-CL outperforms existing methods in financial fraud detection, reducing false positives.
Graph Convolutional Policy for Solving Tree Decomposition via Reinforcement Learning Heuristicscs.LG
We propose a Reinforcement Learning based approach to approximately solve the Tree Decomposition (TD) problem. TD is a combinatorial problem, which is central to the analysis of graph minor structure and computational complexity, as well as in the algorithms of probabilistic inference, register allocation, and other pr…
This paper presents a framework to tackle combinatorial optimization problems using neural networks and reinforcement learning. We focus on the traveling salesman problem (TSP) and train a recurrent network that, given a set of city coordinates, predicts a distribution over different city permutations. Using negative t…
XGNN explains graph neural networks by generating graphs that maximize model predictions.
problem Lack of explainable models for graph neural networks.
method Train a graph generator to maximize model predictions, using reinforcement learning and graph rules.
result Generated graphs provide insights into how GNNs work and can guide model improvement.
Improving the interpretability of GNN predictions through conformal-based graph sparsificationstat.ML
Proposes a method to improve GNN predictions by finding the most predictive subgraph.
problem GNNs aggregate all nodes and edges, making predictions hard to interpret.
method Uses reinforcement learning to find a sparse subgraph that optimizes graph classification performance.
result Our method finds sparser subgraphs that improve interpretability while maintaining performance.
Graph-based state representation improves deep RL performance.
problem High sample-complexity and starting with a good input representation in deep RL.
method Exploiting the graph structure of MDPs for effective state representation learning.
result Graph-based node representation methods outperform matrix-based methods in grid-world navigation tasks.
Paper formalizes a reinforcement learning model for complex information structures.
problem Complex interdependence in sequential decision-making problems.
method Formalizes a novel reinforcement learning model with explicit information structure representation.
result Upper bound on sample complexity of learning general sequential decision-making problems.
Graph neural networks-based Scheduler for Production planning problems using Reinforcement Learningcs.LG
GraSP-RL uses graph neural networks to improve job shop scheduling.
problem Capturing machine-unit-job sequence relationships and managing state space growth.
method Graph neural networks for feature extraction, reinforcement learning for decision-making, decentralized optimization.
result GraSP-RL outperforms existing methods in minimizing makespan for complex production environments.
DRIFT uses RL to automate functional software testing efficiently.
problem Efficient and reliable automated software testing.
method DRIFT employs Q-learning with Graph Neural Networks on symbolic UI representations.
result DRIFT can robustly test software functionalities in a fully automated manner.
Q*BERT learns to navigate text-based games by building a knowledge graph.
problem Text-based games have bottlenecks that standard RL agents struggle to overcome.
method Q*BERT learns a knowledge graph and uses intrinsic motivation to detect and overcome bottlenecks.
result Q*BERT outperforms state-of-the-art agents in text games, including Zork.
IDS improves reinforcement learning with contextual information.
problem Optimizing IDS for contextual reinforcement learning.
method Investigated contextual bandit problems and proposed a computationally-efficient IDS.
result Contextual IDS outperforms conditional IDS by considering future contexts.
Tail-GNNs improve protein function prediction using relational reinforcement.
problem Predicting hierarchical protein functions from sequence data.
method Combining Tail-GNNs with dilated convolutional networks for multi-task learning.
result Significant improvement in F_1 score for protein function prediction.
XLVINs improve deep reinforcement learning by combining self-supervised learning and neural algorithmic reasoning.
problem Limitations of Value Iteration Networks (VINs) in deep reinforcement learning.
method Combining contrastive self-supervised learning, graph representation learning, and neural algorithmic reasoning.
result XLVINs match VIN-like models on discrete, fixed MDPs and significantly outperform model-free baselines.