Inferring Relational Potentials in Interacting Systems

• URL: http://arxiv.org/abs/2310.14466v1
• Date: Mon, 23 Oct 2023 00:44:17 GMT
• Title: Inferring Relational Potentials in Interacting Systems
• Authors: Armand Comas-Massagu\'e, Yilun Du, Christian Fernandez, Sandesh Ghimire, Mario Sznaier, Joshua B. Tenenbaum, Octavia Camps
• Abstract summary: We propose Neural Interaction Inference with Potentials (NIIP) as an alternative approach to discover such interactions. NIIP assigns low energy to the subset of trajectories which respect the relational constraints observed. It allows trajectory manipulation, such as interchanging interaction types across separately trained models, as well as trajectory forecasting.
• Score: 56.498417950856904
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Systems consisting of interacting agents are prevalent in the world, ranging from dynamical systems in physics to complex biological networks. To build systems which can interact robustly in the real world, it is thus important to be able to infer the precise interactions governing such systems. Existing approaches typically discover such interactions by explicitly modeling the feed-forward dynamics of the trajectories. In this work, we propose Neural Interaction Inference with Potentials (NIIP) as an alternative approach to discover such interactions that enables greater flexibility in trajectory modeling: it discovers a set of relational potentials, represented as energy functions, which when minimized reconstruct the original trajectory. NIIP assigns low energy to the subset of trajectories which respect the relational constraints observed. We illustrate that with these representations NIIP displays unique capabilities in test-time. First, it allows trajectory manipulation, such as interchanging interaction types across separately trained models, as well as trajectory forecasting. Additionally, it allows adding external hand-crafted potentials at test-time. Finally, NIIP enables the detection of out-of-distribution samples and anomalies without explicit training. Website: https://energy-based-model.github.io/interaction-potentials.

Related papers

• Diffusion model for relational inference [2.83334745695045]
  We propose a financial price model for systems with observable dynamics. DiffRI learns to infer the probability of presence of connections between components through conditional diffusion modeling.
  arXiv  Detail & Related papers  (2024-01-30T05:25:02Z)
• Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control [63.310780486820796]
  We show how a parameterization of recurrent connectivity influences robustness in closed-loop settings. We find that closed-form continuous-time neural networks (CfCs) with fewer parameters can outperform their full-rank, fully-connected counterparts.
  arXiv  Detail & Related papers  (2023-10-05T21:44:18Z)
• Machine learning the interaction network in coupled dynamical systems [0.0]
  In a collection of interacting particles, the interaction network contains information about how various components interact with one another. In this work, we employ a self-supervised neural network model to achieve two outcomes: to recover the interaction network and to predict the dynamics of individual agents.
  arXiv  Detail & Related papers  (2023-10-05T08:29:00Z)
• Exploiting disorder to probe spin and energy hydrodynamics [6.655372107268362]
  We introduce a novel technique that enables the measurement of local correlation functions, down to single-site resolution. We measure both the spin and energy transport in nuclear spin chains. Interestingly, when the system is both interacting and (nearly-)integrable, we observe the coexistence of diffusive spin transport with ballistic energy transport.
  arXiv  Detail & Related papers  (2022-09-19T19:38:05Z)
• Learning Heterogeneous Interaction Strengths by Trajectory Prediction with Graph Neural Network [0.0]
  We propose the attentive relational inference network (RAIN) to infer continuously weighted interaction graphs without any ground-truth interaction strengths. We show that our RAIN model with the PA mechanism accurately infers continuous interaction strengths for simulated physical systems in an unsupervised manner.
  arXiv  Detail & Related papers  (2022-08-28T09:13:33Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)
• TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild [77.59069361196404]
  TRiPOD is a novel method for predicting body dynamics based on graph attentional networks. To incorporate a real-world challenge, we learn an indicator representing whether an estimated body joint is visible/invisible at each frame. Our evaluation shows that TRiPOD outperforms all prior work and state-of-the-art specifically designed for each of the trajectory and pose forecasting tasks.
  arXiv  Detail & Related papers  (2021-04-08T20:01:00Z)
• Towards Interaction Detection Using Topological Analysis on Neural Networks [55.74562391439507]
  In neural networks, any interacting features must follow a strongly weighted connection to common hidden units. We propose a new measure for quantifying interaction strength, based upon the well-received theory of persistent homology. A Persistence Interaction detection(PID) algorithm is developed to efficiently detect interactions.
  arXiv  Detail & Related papers  (2020-10-25T02:15:24Z)
• Dynamic Relational Inference in Multi-Agent Trajectories [15.602689376767664]
  Inferring interactions from multi-agent trajectories has broad applications in physics, vision and robotics. NRI is a deep generative model that can reason about relations in complex dynamics without supervision. We propose an extension ofNRI, which we call the DYnamic multi-AgentRelational Inference (DYARI) model that can reason about dynamic relations.
  arXiv  Detail & Related papers  (2020-07-16T19:15:16Z)
• Flexible Transmitter Network [84.90891046882213]
  Current neural networks are mostly built upon the MP model, which usually formulates the neuron as executing an activation function on the real-valued weighted aggregation of signals received from other neurons. We propose the Flexible Transmitter (FT) model, a novel bio-plausible neuron model with flexible synaptic plasticity. We present the Flexible Transmitter Network (FTNet), which is built on the most common fully-connected feed-forward architecture.
  arXiv  Detail & Related papers  (2020-04-08T06:55:12Z)

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.