Related papers: Graph In-Context Operator Networks for Generalizab…

Predicting future trajectories of surrounding vehicles heavily relies on what contextual information is given to a motion prediction model. The context itself can be static (lanes, regulatory elements, etc) or dynamic (traffic…

In this note we explore a fully unsupervised deep-learning framework for simulating non-linear structural equation models from observational training data. The main contribution of this note is an architecture for applying moment-matching…

We explore the use of graph neural networks (GNNs) to model spatial processes in which there is no a priori graphical structure. Similar to finite element analysis, we assign nodes of a GNN to spatial locations and use a computational…

Large pre-trained language models (PLMs) have made significant progress in encoding world knowledge and spawned a new set of learning paradigms including zero-shot, few-shot, and in-context learning. Many language tasks can be modeled as a…

In-context learning (ICL) refers to the ability of a model to learn new tasks from examples in its input without any parameter updates. In contrast to previous theories of ICL relying on toy models and data settings, recently it has been…

Convolution Neural Networks on Graphs are important generalization and extension of classical CNNs. While previous works generally assumed that the graph structures of samples are regular with unified dimensions, in many applications, they…

For joint inference over multiple variables, a variety of structured prediction techniques have been developed to model correlations among variables and thereby improve predictions. However, many classical approaches suffer from one of two…

Graph Neural Networks (GNNs) have emerged as a powerful tool to capture intricate network patterns, achieving success across different domains. However, existing GNNs require careful domain-specific architecture designs and training from…

Traffic flow forecasting is a highly challenging task due to the dynamic spatial-temporal road conditions. Graph neural networks (GNN) has been widely applied in this task. However, most of these GNNs ignore the effects of time-varying road…

Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a…

Graph neural networks have shown remarkable success in exploiting the spatial and temporal patterns on dynamic graphs. However, existing GNNs exhibit poor generalization ability under distribution shifts, which is inevitable in dynamic…

Graph Neural Networks (GNNs) are emerging as powerful tools for nonlinear Model Order Reduction (MOR) of time-dependent parameterized Partial Differential Equations (PDEs). However, existing methodologies struggle to combine geometric…

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…

Predicting future motion based on historical motion sequence is a fundamental problem in computer vision, and it has wide applications in autonomous driving and robotics. Some recent works have shown that Graph Convolutional Networks(GCN)…

Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model. Here we introduce a new…

From a telecommunication standpoint, the surge in users and services challenges next-generation networks with escalating traffic demands and limited resources. Accurate traffic prediction can offer network operators valuable insights into…

Modern machine learning requires system designers to specify aspects of the learning pipeline, such as losses, architectures, and optimizers. Meta-learning, or learning-to-learn, instead aims to learn those aspects, and promises to unlock…

Real-time assessment of near-term Air Traffic Controller (ATCO) task demand is a critical challenge in an increasingly crowded airspace, as existing complexity metrics often fail to capture nuanced operational drivers beyond simple aircraft…

Learning in the space-time domain remains a very challenging problem in machine learning and computer vision. Current computational models for understanding spatio-temporal visual data are heavily rooted in the classical single-image based…

Spatio-temporal graph neural networks (STGNN) have become the most popular solution to traffic forecasting. While successful, they rely on the message passing scheme of GNNs to establish spatial dependencies between nodes, and thus…