Related papers: Learning Parameterized Task Structure for Generali…

Imitation is a basic updating mechanism for strategy evolution in structured populations, determining how individuals sample social information and translate it into behavioral changes. Higher-order networks, such as hypergraphs, generalize…

We present a framework for learning to plan hierarchically in domains with unknown dynamics. We enhance planning performance by exploiting problem structure in several ways: (i) We simplify the search over plans by leveraging knowledge of…

Representation learning is a fundamental task in machine learning, aiming at uncovering structures from data to facilitate subsequent tasks. However, what is a good representation for planning and reasoning in a stochastic world remains an…

Transformers can under some circumstances generalize to novel problem instances whose constituent parts might have been encountered during training, but whose compositions have not. What mechanisms underlie this ability for compositional…

Decision-making in complex systems often relies on machine learning models, yet highly accurate models such as XGBoost and neural networks can obscure the reasoning behind their predictions. In operations research applications,…

Transferring latent structure from one environment or problem to another is a mechanism by which humans and animals generalize with very little data. Inspired by cognitive and neurobiological insights, we propose graph schemas as a…

Real-world data is represented in both structured (e.g., graph connections) and unstructured (e.g., textual, visual information) formats, encompassing complex relationships that include explicit links (such as social connections and user…

We present methods for multi-task learning that take advantage of natural groupings of related tasks. Task groups may be defined along known properties of the tasks, such as task domain or language. Such task groups represent supervised…

Our goal is to generate a policy to complete an unseen task given just a single video demonstration of the task in a given domain. We hypothesize that to successfully generalize to unseen complex tasks from a single video demonstration, it…

Graph representation learning has demonstrated improved performance in tasks such as link prediction and node classification across a range of domains. Research has shown that many natural graphs can be organized in hierarchical…

Many scientific datasets are of high dimension, and the analysis usually requires visual manipulation by retaining the most important structures of data. Principal curve is a widely used approach for this purpose. However, many existing…

This work extends the theory of identifiability in supervised learning by considering the consequences of having access to a distribution of tasks. In such cases, we show that linear identifiability is achievable in the general multi-task…

Graphs provide a natural representation of relational structure that arises across diverse domains. Despite this ubiquity, graph structure is typically learned in a modality- and task-isolated manner, where graph representations are…

This paper presents a novel multi-task learning-based method for unsupervised domain adaptation. Specifically, the source and target domain classifiers are jointly learned by considering the geometry of target domain and the divergence…

Images are composed as a hierarchy of object parts. We use this insight to create a generative graphical model that defines a hierarchical distribution over image parts. Typically, this leads to intractable inference due to loops in the…

Multitask learning is a framework that enforces multiple learning tasks to share knowledge to improve their generalization abilities. While shallow multitask learning can learn task relations, it can only handle predefined features. Modern…

We formalise the essential data of objective functions as equality constraints on composites of learners. We call these constraints "tasks", and we investigate the idealised view that such tasks determine model behaviours. We develop a…

Panoptic Part Segmentation (PPS) aims to unify panoptic segmentation and part segmentation into one task. Previous work mainly utilizes separated approaches to handle thing, stuff, and part predictions individually without performing any…

While large language models have become the prevailing approach for agentic reasoning and planning, their success in symbolic domains does not readily translate to the physical world. Spatial intelligence, the ability to perceive 3D…

Imitation learning has gained immense popularity because of its high sample-efficiency. However, in real-world scenarios, where the trajectory distribution of most of the tasks dynamically shifts, model fitting on continuously aggregated…