6 citations · 27 across the 17 of their papers we have counts for
18 papers
Identifying ODEs from Unstructured Data with Causal Representation Learning
Alessandro Trenta, Riccardo Massidda, Davide Bacciu +1
We study the problem of recovering the governing ODE of a dynamical system from unstructured, high-dimensional observations such as images. Existing methods for ODE discovery typic…
Learning Interactive World Model for Object-Centric Reinforcement Learning
Fan Feng, Phillip Lippe, Sara Magliacane
Agents that understand objects and their interactions can learn policies that are more robust and transferable. However, most object-centric RL methods factor state by individual o…
Combining Causal Models for More Accurate Abstractions of Neural Networks
Theodora-Mara Pîslar, Sara Magliacane, Atticus Geiger
Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when…
Learning to Defer for Causal Discovery with Imperfect Experts
Oscar Clivio, Divyat Mahajan, Perouz Taslakian +4
Integrating expert knowledge, e.g. from large language models, into causal discovery algorithms can be challenging when the knowledge is not guaranteed to be correct. Expert recomm…
Amortized Equation Discovery in Hybrid Dynamical Systems
Yongtuo Liu, Sara Magliacane, Miltiadis Kofinas +1
Hybrid dynamical systems are prevalent in science and engineering to express complex systems with continuous and discrete states. To learn the laws of systems, all previous methods…
Learning Causal Abstractions of Linear Structural Causal Models
Riccardo Massidda, Sara Magliacane, Davide Bacciu
The need for modelling causal knowledge at different levels of granularity arises in several settings. Causal Abstraction provides a framework for formalizing this problem by relat…
Towards the Reusability and Compositionality of Causal Representations
Davide Talon, Phillip Lippe, Stuart James +2
Causal Representation Learning (CRL) aims at identifying high-level causal factors and their relationships from high-dimensional observations, e.g., images. While most CRL works fo…
A Sparsity Principle for Partially Observable Causal Representation Learning
Danru Xu, Dingling Yao, Sébastien Lachapelle +4
Causal representation learning aims at identifying high-level causal variables from perceptual data. Most methods assume that all latent causal variables are captured in the high-d…
Multi-View Causal Representation Learning with Partial Observability
Dingling Yao, Danru Xu, Sébastien Lachapelle +5
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partial…
Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning
Fan Feng, Sara Magliacane
In many reinforcement learning tasks, the agent has to learn to interact with many objects of different types and generalize to unseen combinations and numbers of objects. Often a…
BISCUIT: Causal Representation Learning from Binary Interactions
Phillip Lippe, Sara Magliacane, Sindy Löwe +3
Identifying the causal variables of an environment and how to intervene on them is of core value in applications such as robotics and embodied AI. While an agent can commonly inter…
Graph Switching Dynamical Systems
Yongtuo Liu, Sara Magliacane, Miltiadis Kofinas +1
Dynamical systems with complex behaviours, e.g. immune system cells interacting with a pathogen, are commonly modelled by splitting the behaviour into different regimes, or modes,…
Modulated Neural ODEs
Ilze Amanda Auzina, Çağatay Yıldız, Sara Magliacane +2
Neural ordinary differential equations (NODEs) have been proven useful for learning non-linear dynamics of arbitrary trajectories. However, current NODE methods capture variations…
Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems
Phillip Lippe, Sara Magliacane, Sindy Löwe +3
Causal representation learning is the task of identifying the underlying causal variables and their relations from high-dimensional observations, such as images. Recent work has sh…
Factored Adaptation for Non-Stationary Reinforcement Learning
Fan Feng, Biwei Huang, Kun Zhang +1
Dealing with non-stationarity in environments (e.g., in the transition dynamics) and objectives (e.g., in the reward functions) is a challenging problem that is crucial in real-wor…
CITRIS: Causal Identifiability from Temporal Intervened Sequences
Phillip Lippe, Sara Magliacane, Sindy Löwe +3
Understanding the latent causal factors of a dynamical system from visual observations is considered a crucial step towards agents reasoning in complex environments. In this paper,…
AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning
Biwei Huang, Fan Feng, Chaochao Lu +2
One practical challenge in reinforcement learning (RL) is how to make quick adaptations when faced with new environments. In this paper, we propose a principled framework for adapt…
Active Structure Learning of Causal DAGs via Directed Clique Tree
Chandler Squires, Sara Magliacane, Kristjan Greenewald +3
A growing body of work has begun to study intervention design for efficient structure learning of causal directed acyclic graphs (DAGs). A typical setting is a causally sufficient…