Self-Predictive Representations improves data-efficient reinforcement learning from limited interaction.
problem Efficient reinforcement learning from limited data.
method Train agents to predict future latent state representations using self-supervised objectives.
result Achieves a median human-normalized score of 0.415 on Atari with 100k steps of interaction, 55% improvement over previous state-of-the-art.
Graph neural network predicts vehicle interactions and trajectories for autonomous driving.
problem Predicting future motion of vehicles in traffic scenes.
method Graph neural network that jointly predicts interaction modes and 5-second future trajectories.
result Jointly predicting trajectories and interaction modes leads to lower trajectory error.
RE-NET predicts future interactions in temporal knowledge graphs.
problem Predicting future facts in temporal knowledge graphs.
method Autoregressive architecture with recurrent event encoder and neighborhood aggregator.
result State-of-the-art performance on five public datasets.
Modeling a sequence of interactions between users and items (e.g., products, posts, or courses) is crucial in domains such as e-commerce, social networking, and education to predict future interactions. Representation learning presents an attractive solution to model the dynamic evolution of user and item properties, w…
Predicts multiple vehicle trajectories efficiently.
problem Predicting uncertain future motions of agents in dynamic scenes.
method Probabilistic framework learning latent variables for multi-step future modeling.
result State-of-the-art predictions on vehicle trajectory datasets.
This work analyzes the value of future reward information in RL.
problem Analyzing the impact of knowing future rewards in reinforcement learning.
method Competitive analysis and worst-case reward distribution.
result Exact ratios between standard RL agents and those with future-reward lookahead.
Traffic actors' future motion predicted using a hybrid graph model.
problem Predicting long-term behaviors of traffic actors in complex scenes.
method A hybrid graph model with nodes for actors and traffic elements, and edges for interaction types.
result TrafficGraphNet achieves state-of-the-art trajectory prediction accuracy.
Proposes a new model for predicting future motion of road actors in autonomous vehicles.
problem Forecasting the long-term future motion of road actors for safe autonomous driving.
method Recurrent graph-based attentional approach with interpretable geometric and social relationships.
result Can produce diverse predictions conditioned on hypothetical or 'what-if' scenarios.
Study examines lead-lag relationships between VIX and VIX futures markets over time.
problem Understanding dynamic interaction patterns between VIX and VIX futures markets.
method Utilized the symmetric thermal optimal path (TOPS) method to analyze time-dependent lead-lag relationships.
result Observed alternate lead-lag relationship instead of dominance between VIX and VIX futures markets.
Autonomous vehicles (AVs) are on the road. To safely and efficiently interact with other road participants, AVs have to accurately predict the behavior of surrounding vehicles and plan accordingly. Such prediction should be probabilistic, to address the uncertainties in human behavior. Such prediction should also be in…
We present an approach for building an active agent that learns to segment its visual observations into individual objects by interacting with its environment in a completely self-supervised manner. The agent uses its current segmentation model to infer pixels that constitute objects and refines the segmentation model …
Paper proposes a multi-modal probabilistic prediction model for interactive behavior.
problem Predicting future motions of interacting entities in real-world scenarios.
method Generative model for joint prediction of sequential motions of interacting agents.
result Interpretable model capable of handling prediction uncertainties and multi-modal distributions.
System predicts vehicle interactions and trajectories with uncertainty.
problem Predicting future vehicle trajectories with uncertainty.
method Hierarchical Bayesian Generative Modeling with categorized and real-valued coordination variables.
result Categorized coordination better captures multi-modality and generates more diverse samples.
Interactive model analysis, the process of understanding, diagnosing, and refining a machine learning model with the help of interactive visualization, is very important for users to efficiently solve real-world artificial intelligence and data mining problems. Dramatic advances in big data analytics has led to a wide …
Paper predicts future vehicle trajectories for safer AVs.
problem Improving accuracy of long-term vehicle trajectory prediction for autonomous vehicles.
method Dual LSTM network for automatic learning of driver behaviors and future trajectory prediction.
result The method achieves lower RMSE for longitudinal and lateral predictions compared to state-of-the-art methods.
PRECOG predicts future interactions between AVs and other drivers.
problem Autonomous vehicles need to predict human drivers' intentions for safe road behavior.
method Probabilistic forecasting model trained on real and simulated data.
result Our model predicts future interactions more accurately than existing methods.
Neural production systems learn visual dynamics by applying rule templates to entities.
problem Modeling interactions among entities in structured visual environments.
method Inspired by production systems, the paper uses rule templates to bind placeholder variables to specific entities, scoring and applying the best fitting rules to update entity properties.
result The architecture achieves robust future-state prediction and extrapolation from simple to complex environments, outperforming GNNs.
Polluting fine dusts in South Korea which are mainly consisted of biomass burning and fugitive dust blown from dust belt is significant problem these days. Predicting concentrations of fine dust particles in Seoul is challenging because they are product of complicate chemical reactions among gaseous pollutants and also…
Many recommendation algorithms rely on user data to generate recommendations. However, these recommendations also affect the data obtained from future users. This work aims to understand the effects of this dynamic interaction. We propose a simple model where users with heterogeneous preferences arrive over time. Based…
Model assesses systemic risk in crude oil and gasoline futures markets.
problem Systemic risk in high-frequency crude oil and gasoline futures markets.
method Hawkes flocking model examining endogeneity and interactivity.
result Significantly higher endogenous systemic risk in WTI crude oil compared to gasoline, with gasoline having a higher influence on WTI.
Interactive tool helps RL researchers debug and understand their models.
problem Challenges in debugging reinforcement learning algorithms.
method Design and implementation of an interactive visualization tool.
result Addresses features missing from previous tools for RL.
Autoencoder learns group representations from actions, improving future prediction accuracy.
problem Learning internal models of interactions with the real world.
method Homomorphism autoencoder with group representation trained on equivariance-derived loss.
result Agents can predict future actions with improved accuracy.
Bi-GNN models drug interactions using a bi-level graph approach.
problem Predicting drug-drug interactions using machine learning.
method Bi-level graph neural networks that consider both interaction graph and representation graphs of drugs.
result Bi-GNN model improves DDI prediction accuracy compared to existing methods.
This work creates a system for understanding human movement in spaces.
problem Simplify communication and interaction between robots and humans in spatial tasks.
method Uses unsupervised learning with neural autoencoding to learn continuous representations of spatio-temporal trajectory data.
result Proposes a method to form prototypical representations of movement based on spatial context.
Proposes MLCNN for better multivariate time series forecasting.
problem Challenges in forecasting multivariate time series, especially the limitation of predicting only one future moment.
method MLCNN, a multi-task deep learning framework inspired by Construal Level Theory, fuses future visions of near and distant future predictions.
result Significant improvements in forecasting accuracy (4.59% RMSE reduction, 6.87% MAE reduction) on real-world datasets.
Model generates music to connect missing parts, leveraging latent space of VAE.
problem Music inpainting from missing or lost information.
method Deep learning model using VAE latent space and RNN to traverse latent space conditioned on past and future musical contexts.
result Model generates meaningful music inpaintings, connecting musical excerpts.
We present a method that learns to integrate temporal information, from a learned dynamics model, with ambiguous visual information, from a learned vision model, in the context of interacting agents. Our method is based on a graph-structured variational recurrent neural network (Graph-VRNN), which is trained end-to-end…
STOVE predicts convincing physical behavior in videos.
problem Learning models from videos with objects and interactions.
method Compositional state-space model combining image and dynamics models.
result Predicts videos with convincing physical behavior over hundreds of timesteps.
Paper proposes a reinforcement learning method for trading using expert trajectories.
problem Inability of existing methods to handle long-term goals and delayed rewards in futures trading.
method Modeling futures trading as MDP, using reinforcement learning with expert trajectories and multiple short-term alpha factors.
result The proposed method outperforms traditional and deep learning methods in trading performance.
We propose a latent self-exciting point process model that describes geographically distributed interactions between pairs of entities. In contrast to most existing approaches that assume fully observable interactions, here we consider a scenario where certain interaction events lack information about participants. Ins…
Proposes a new framework for resource-limited recommendation.
problem Resource constraints affect user choices in recommendation tasks.
method Interest-behavior multiplicative network with MRRNNs and resource-limited branch.
result Framework effectively predicts user interactions considering resource limitations.
Predicting movement of objects while the action of learning agent interacts with the dynamics of the scene still remains a key challenge in robotics. We propose a multi-layer Long Short Term Memory (LSTM) autoendocer network that predicts future frames for a robot navigating in a dynamic environment with moving obstacl…
Model discovers causal relationships from video data of physical systems.
problem Discover structural dependencies and causal interactions in physical systems from video data.
method End-to-end model with perception, inference, and dynamics modules; handles unknown interventions.
result Model correctly identifies causal interactions and makes long-term predictions.
Interactive machine learning improves learning efficiency with user input.
problem Expensive, time-consuming, or risky acquisition of labeled data and decision-making.
method Develops new algorithms for active learning, sequential decision making, and model selection under partial feedback.
result First efficient algorithms achieving exponential label savings and independent of action space size.
DiffLOB models future market conditions for better decision-making.
problem Passive generative models cannot explore hypothetical market scenarios.
method Regime-conditioned diffusion model for counterfactual LOB generation.
result DiffLOB enables realistic and controllable generation of LOB trajectories.
Study on predictable forward processes in trading without frequent evaluations.
problem Trading performance evaluation times not matching trading times.
method Solving a linear functional equation to construct predictable forward processes.
result Predictable forward processes are inherently myopic and optimal strategies do not use future information.
This work discovers latent field effects governing interacting dynamical systems.
problem Discovering field effects governing interacting dynamical systems.
method Proposes neural fields to learn latent force fields from observed dynamics, disentangling local object interactions and global field effects.
result Accurately discovers latent field effects in various dynamical systems.
Survey reviews machine learning for automatic movement generation.
problem Need for automatic movement animation in interactive media.
method Machine learning techniques and motion capture data.
result Discussion of research gaps and challenges for future work.
Aims to learn from multiple unpredictable teachers with minimal interaction.
problem Learning from multiple non-deterministic teachers with low interaction cost.
method Develops a framework and an active learning algorithm to estimate a distribution over policy space.
result Significantly reduces interaction with teachers without compromising performance.
Proposes a graph neural network for futures price prediction.
problem Challenges in high-frequency trading of futures prices.
method Heterogeneous Continual Graph Neural Network (STGNN) integrating multi-factor pricing theories.
result Outperforms other models in prediction accuracy on 49 commodity futures.
The paper proposes a model to forecast traffic motion from sensor data.
problem Accurately predicting traffic motion for safe vehicle maneuvers.
method Implicit latent variable model using interaction graphs and graph neural networks.
result Achieves state-of-the-art motion forecasting and interaction understanding.
SPARTAN learns sparse interaction graphs between objects in scenes.
problem Capturing structured interactions between entities in complex settings remains challenging.
method SPARTAN is a Transformer-based world model that learns sparse, context-dependent interaction graphs through sparsity regularization on attention patterns.
result SPARTAN achieves significantly improved few-shot adaptation to dynamics changes and robustness against distractors.
MIDAS learns to adaptively control other cars in urban driving scenarios.
problem Autonomous vehicles need to interact with other agents on the road.
method Reinforcement learning with attention mechanism to handle multiple agents.
result MIDAS policies are adaptive and robust to external changes.
Model analyzes trading frictions in cap-and-trade markets, showing how they interact to affect market effectiveness.
problem Analyzing how trading frictions impact cap-and-trade market effectiveness.
method Developed a dynamic stochastic model with multiple trading frictions, characterized access choices in closed form, and quantified using EU ETS data.
result Trading frictions interact to amplify or dampen market responses, and their combined effect is non-additive.
We present a new package in R implementing Bayesian additive regression trees (BART). The package introduces many new features for data analysis using BART such as variable selection, interaction detection, model diagnostic plots, incorporation of missing data and the ability to save trees for future prediction. It is …
This Perspective provides examples of current and future applications of deep learning in pharmacogenomics, including: (1) identification of novel regulatory variants located in noncoding domains and their function as applied to pharmacoepigenomics; (2) patient stratification from medical records; and (3) prediction of…
New method calibrates MQHawkes model using non-parametric approach, identifying cross-Hawkes and cross-leverage effects.
problem Calibrating complex Hawkes processes with non-parametric methods.
method Non-parametric calibration using General Method of Moments on coarse-grained MQHawkes model.
result Identification of cross-Hawkes and cross-leverage effects in futures markets.
Interactive Machine Learning (IML) is an iterative learning process that tightly couples a human with a machine learner, which is widely used by researchers and practitioners to effectively solve a wide variety of real-world application problems. Although recent years have witnessed the proliferation of IML in the fiel…