Neural Relational Inference with Fast Modular Meta-learning

• URL: http://arxiv.org/abs/2310.07015v1
• Date: Tue, 10 Oct 2023 21:05:13 GMT
• Title: Neural Relational Inference with Fast Modular Meta-learning
• Authors: Ferran Alet, Erica Weng, Tom\'as Lozano P\'erez, Leslie Pack Kaelbling
• Abstract summary: Graph neural networks (GNNs) are effective models for many dynamical systems consisting of entities and relations. Relational inference is the problem of inferring these interactions and learning the dynamics from observational data. We frame relational inference as a textitmodular meta-learning problem, where neural modules are trained to be composed in different ways to solve many tasks.
• Score: 25.313516707169498
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: \textit{Graph neural networks} (GNNs) are effective models for many dynamical systems consisting of entities and relations. Although most GNN applications assume a single type of entity and relation, many situations involve multiple types of interactions. \textit{Relational inference} is the problem of inferring these interactions and learning the dynamics from observational data. We frame relational inference as a \textit{modular meta-learning} problem, where neural modules are trained to be composed in different ways to solve many tasks. This meta-learning framework allows us to implicitly encode time invariance and infer relations in context of one another rather than independently, which increases inference capacity. Framing inference as the inner-loop optimization of meta-learning leads to a model-based approach that is more data-efficient and capable of estimating the state of entities that we do not observe directly, but whose existence can be inferred from their effect on observed entities. To address the large search space of graph neural network compositions, we meta-learn a \textit{proposal function} that speeds up the inner-loop simulated annealing search within the modular meta-learning algorithm, providing two orders of magnitude increase in the size of problems that can be addressed.

Related papers

• Interaction Event Forecasting in Multi-Relational Recursive HyperGraphs: A Temporal Point Process Approach [12.142292322071299]
  This work addresses the problem of forecasting higher-order interaction events in multi-relational recursive hypergraphs. The proposed model, textitRelational Recursive Hyperedge Temporal Point Process (RRHyperTPP), uses an encoder that learns a dynamic node representation based on the historical interaction patterns. We have experimentally shown that our models perform better than previous state-of-the-art methods for interaction forecasting.
  arXiv  Detail & Related papers  (2024-04-27T15:46:54Z)
• Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN [20.380620709345898]
  Early-exiting dynamic neural networks (EDNN) allow a model to make some of its predictions from intermediate layers (i.e., early-exit) Training an EDNN architecture is challenging as it consists of two intertwined components: the gating mechanism (GM) that controls early-exiting decisions and the intermediate inference modules (IMs) that perform inference from intermediate representations. We propose a novel architecture that connects these two modules. This leads to significant performance improvements on classification datasets and enables better uncertainty characterization capabilities.
  arXiv  Detail & Related papers  (2023-10-13T14:56:38Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• Dynamic Relation Discovery and Utilization in Multi-Entity Time Series Forecasting [92.32415130188046]
  In many real-world scenarios, there could exist crucial yet implicit relation between entities. We propose an attentional multi-graph neural network with automatic graph learning (A2GNN) in this work.
  arXiv  Detail & Related papers  (2022-02-18T11:37:04Z)
• Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
  We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
  arXiv  Detail & Related papers  (2021-07-08T18:01:02Z)
• Convolutions for Spatial Interaction Modeling [9.408751013132624]
  We consider the problem of spatial interaction modeling in the context of predicting the motion of actors around autonomous vehicles. We revisit convolutions and show that they can demonstrate comparable performance to graph networks in modeling spatial interactions with lower latency.
  arXiv  Detail & Related papers  (2021-04-15T00:41:30Z)
• TrackMPNN: A Message Passing Graph Neural Architecture for Multi-Object Tracking [8.791710193028903]
  This study follows many previous approaches to multi-object tracking (MOT) that model the problem using graph-based data structures. We create a framework based on dynamic undirected graphs that represent the data association problem over multiple timesteps. We also provide solutions and propositions for the computational problems that need to be addressed to create a memory-efficient, real-time, online algorithm.
  arXiv  Detail & Related papers  (2021-01-11T21:52:25Z)
• Network Diffusions via Neural Mean-Field Dynamics [52.091487866968286]
  We propose a novel learning framework for inference and estimation problems of diffusion on networks. Our framework is derived from the Mori-Zwanzig formalism to obtain an exact evolution of the node infection probabilities. Our approach is versatile and robust to variations of the underlying diffusion network models.
  arXiv  Detail & Related papers  (2020-06-16T18:45:20Z)
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks [91.65637773358347]
  We propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module. Our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets.
  arXiv  Detail & Related papers  (2020-05-24T04:02:18Z)
• Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems [83.98774574197613]
  We take one of the simplest inference methods, a truncated max-product Belief propagation, and add what is necessary to make it a proper component of a deep learning model. This BP-Layer can be used as the final or an intermediate block in convolutional neural networks (CNNs) The model is applicable to a range of dense prediction problems, is well-trainable and provides parameter-efficient and robust solutions in stereo, optical flow and semantic segmentation.
  arXiv  Detail & Related papers  (2020-03-13T13:11:35Z)
• Relational State-Space Model for Stochastic Multi-Object Systems [24.234120525358456]
  This paper introduces the relational state-space model (R-SSM), a sequential hierarchical latent variable model. R-SSM makes use of graph neural networks (GNNs) to simulate the joint state transitions of multiple correlated objects. The utility of R-SSM is empirically evaluated on synthetic and real time-series datasets.
  arXiv  Detail & Related papers  (2020-01-13T03:45:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.