When Medical Imaging Met Self-Attention: A Love Story That Didn't Quite Work Out

A substantial body of research has focused on developing systems that assist medical professionals during labor-intensive early screening processes, many based on convolutional deep-learning architectures. Recently, multiple studies explored the application of so-called self-attention mechanisms in the vision domain. These studies often report empirical improvements over fully convolutional approaches on various datasets and tasks. To evaluate this trend for medical imaging, we extend two widely adopted convolutional architectures with different self-attention variants on two different medical datasets. With this, we aim to specifically evaluate the possible advantages of additional self-attention. We compare our models with similarly sized convolutional and attention-based baselines and evaluate performance gains statistically. Additionally, we investigate how including such layers changes the features learned by these models during the training. Following a hyperparameter search, and contrary to our expectations, we observe no significant improvement in balanced accuracy over fully convolutional models. We also find that important features, such as dermoscopic structures in skin lesion images, are still not learned by employing self-attention. Finally, analyzing local explanations, we confirm biased feature usage. We conclude that merely incorporating attention is insufficient to surpass the performance of existing fully convolutional methods.

Reducing Bias in Pre-trained Models by Tuning while Penalizing Change

Deep models trained on large amounts of data often incorporate implicit biases present during training time. If later such a bias is discovered during inference or deployment, it is often necessary to acquire new data and retrain the model. This behavior is especially problematic in critical areas such as autonomous driving or medical decision-making. In these scenarios, new data is often expensive and hard to come by. In this work, we present a method based on change penalization that takes a pre-trained model and adapts the weights to mitigate a previously detected bias. We achieve this by tuning a zero-initialized copy of a frozen pre-trained network. Our method needs very few, in extreme cases only a single, examples that contradict the bias to increase performance. Additionally, we propose an early stopping criterion to modify baselines and reduce overfitting. We evaluate our approach on a well-known bias in skin lesion classification and three other datasets from the domain shift literature. We find that our approach works especially well with very few images. Simple fine-tuning combined with our early stopping also leads to performance benefits for a larger number of tuning samples.

Embracing the black box: Heading towards foundation models for causal discovery from time series data

Causal discovery from time series data encompasses many existing solutions, including those based on deep learning techniques. However, these methods typically do not endorse one of the most prevalent paradigms in deep learning: End-to-end learning. To address this gap, we explore what we call Causal Pretraining. A methodology that aims to learn a direct mapping from multivariate time series to the underlying causal graphs in a supervised manner. Our empirical findings suggest that causal discovery in a supervised manner is possible, assuming that the training and test time series samples share most of their dynamics. More importantly, we found evidence that the performance of Causal Pretraining can increase with data and model size, even if the additional data do not share the same dynamics. Further, we provide examples where causal discovery for real-world data with causally pretrained neural networks is possible within limits. We argue that this hints at the possibility of a foundation model for causal discovery.

Stabilizing Transformer-Based Action Sequence Generation For Q-Learning

Since the publication of the original Transformer architecture (Vaswani et al. 2017), Transformers revolutionized the field of Natural Language Processing. This, mainly due to their ability to understand timely dependencies better than competing RNN-based architectures. Surprisingly, this architecture change does not affect the field of Reinforcement Learning (RL), even though RNNs are quite popular in RL, and time dependencies are very common in RL. Recently, (Parisotto et al. 2019) conducted the first promising research of Transformers in RL. To support the findings of this work, this paper seeks to provide an additional example of a Transformer-based RL method. Specifically, the goal is a simple Transformer-based Deep Q-Learning method that is stable over several environments. Due to the unstable nature of Transformers and RL, an extensive method search was conducted to arrive at a final method that leverages developments around Transformers as well as Q-learning. The proposed method can match the performance of classic Q-learning on control environments while showing potential on some selected Atari benchmarks. Furthermore, it was critically evaluated to give additional insights into the relation between Transformers and RL.

Jacobian Policy Optimizations

Recently, natural policy gradient algorithms gained widespread recognition due to their strong performance in reinforcement learning tasks. However, their major drawback is the need to secure the policy being in a ``trust region'' and meanwhile allowing for sufficient exploration. The main objective of this study was to present an approach which models dynamical isometry of agents policies by estimating conditioning of its Jacobian at individual points in the environment space. We present a Jacobian Policy Optimization algorithm for policy optimization, which dynamically adapts the trust interval with respect to policy conditioning. The suggested approach was tested across a range of Atari environments. This paper offers some important insights into an improvement of policy optimization in reinforcement learning tasks.