The van der Schaar Lab will be represented at the Tenth International Conference on Learning Representations (ICLR 2022) with 5 papers accepted for publication. Of these papers, 3 have been chosen by the organisers to be Spotlight Presentations. Out of the big three major machine learning and AI conferences, ICLR is regarded as the one with the highest impact.
ICLR, running from 25 – 29 April, is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science.
Collectively, these papers touch on some of the most important areas within the lab’s extensive research agenda, including quantitative epistemology, discovery using machine learning, and self- and semi-supervised learning.
Details regarding the 5 papers can be found below.
[Spotlight] D-CODE: Discovering Closed-form ODEs from Observed Trajectories
For centuries, scientists have manually designed closed-form ordinary differential equations (ODEs) to model dynamical systems. An automated tool to distill closed-form ODEs from observed trajectories would accelerate the modeling process. Traditionally, symbolic regression is used to uncover a closed-form prediction function a = f(b) with label-features (ai, bi) as training examples,
However, an ODE models the time derivative x(t) of a dynamical system, e.g. x(t) = f(x(t),t), and the “label” x(t) is usually *not* observed. The existing ways to bridge this gap only perform well for a narrow range of settings with low measurement noise, frequent sampling, and non-chaotic dynamics. In this work, we propose the Discovery of Closed-form ODE framework (D-CODE), which advances symbolic regression beyond the paradigm of supervised learning.
D-CODE leverages a novel objective function based on the variational formulation of ODEs to bypass the unobserved time derivative. For formal justification, we prove that this objective is a valid proxy for the estimation error of the true (but unknown) ODE. In the experiments, D-CODE successfully discovered the governing equations of a diverse range of dynamical systems under challenging measurement settings with high noise and infrequent sampling.
[Spotlight] Self-Supervision Enhanced Feature Selection with Correlated Gases
Discovering relevant input features for predicting a target variable is a key scientific question. However, in many domains, such as medicine and biology, feature selection is confounded by a scarcity of labeled samples coupled with significant correlations among features.
In this paper, we propose a novel deep learning approach to feature selection that addresses both challenges simultaneously. First, we pre-train the network using unlabeled samples within a self-supervised learning framework by solving pretext tasks that require the network to learn informative representations from partial feature sets. Then, we fine-tune the pre-trained network to discover relevant features using labeled samples. During both training phases, we explicitly account for the correlation structure of the input features by generating correlated gate vectors from a multivariate Bernoulli distribution.
Experiments on multiple real-world datasets including clinical and omics demonstrate that our model discovers relevant features that provide superior prediction performance compared to the state-of-the-art benchmarks in practical scenarios where there is often limited labeled data and high correlations among features.
Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies
Human decision making is well known to be imperfect and the ability to analyse such processes individually is crucial when attempting to aid or improve a decision-maker’s ability to perform a task, e.g. to alert them to potential biases or oversights on their part.
To do so, it is necessary to develop interpretable representations of how agents make decisions and how this process changes over time as the agent learns online in reaction to the accrued experience. To then understand the decision-making processes underlying a set of observed trajectories, we cast the policy inference problem as the inverse to this online learning problem. By interpreting actions within a potential outcomes framework, we introduce a meaningful mapping based on agents choosing an action they believe to have the greatest treatment effect.
We introduce a practical algorithm for retrospectively estimating such perceived effects, alongside the process through which agents update them, using a novel architecture built upon an expressive family of deep state-space models. Through application to the analysis of UNOS organ donation acceptance decisions, we demonstrate that our approach can bring valuable insights into the factors that govern decision processes and how they change over time.
[Spotlight] POETREE: Interpretable Policy Learning with Adaptive Decision Trees
Building models of human decision-making from observed behaviour is critical to better understand, diagnose and support real-world policies such as clinical care. As established policy learning approaches remain focused on imitation performance, they fall short of explaining the demonstrated decision-making process.
Policy Extraction through decision Trees (POETREE) is a novel framework for interpretable policy learning, compatible with fully-offline and partially-observable clinical decision environments — and builds probabilistic tree policies determining physician actions based on patients’ observations and medical history. Fully-differentiable tree architectures are grown incrementally during optimization to adapt their complexity to the modelling task, and learn a representation of patient history through recurrence, resulting in decision tree policies that adapt over time with patient information.
This policy learning method outperforms the state-of-the-art on real and synthetic medical datasets, both in terms of understanding, quantifying and evaluating observed behaviour as well as in accurately replicating it — with potential to improve future decision support systems.
Neural graphical modelling in continuous-time: consistency guarantees and algorithms
The discovery of structure from time series data is a key problem in fields of study working with complex systems. Most identifiability results and learning algorithms assume the underlying dynamics to be discrete in time. Comparatively few, in contrast, explicitly define dependencies in infinitesimal intervals of time, independently of the scale of observation and of the regularity of sampling.
In this paper, we consider score-based structure learning for the study of dynamical systems. We prove that for vector fields parameterized in a large class of neural networks, least squares optimization with adaptive regularization schemes consistently recovers directed graphs of local independencies in systems of stochastic differential equations.
Using this insight, we propose a score-based learning algorithm based on penalized Neural Ordinary Differential Equations (modelling the mean process) that we show to be applicable to the general setting of irregularly-sampled multivariate time series and to outperform the state of the art across a range of dynamical systems.
The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning.
ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.
Participants at ICLR span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
For a full list of the van der Schaar Lab’s publications, click here.