The explainability of deep learning models remains a significant challenge, particularly in the medical domain where interpretable outputs are critical for clinical trust and transparency. Path attribution methods such as Integrated Gradients rely on a baseline representing the absence of relevant features ("missingness"). Commonly used baselines, such as all-zero inputs, are often semantically meaningless, especially in medical contexts. While alternative baseline choices have been explored, existing methods lack a principled approach to dynamically select baselines tailored to each input. In this work, we examine the notion of missingness in the medical context, analyze its implications for baseline selection, and introduce a counterfactual-guided approach to address the limitations of conventional baselines. We argue that a generated counterfactual (i.e. clinically "normal" variation of the pathological input) represents a more accurate representation of a meaningful absence of features. We use a Variational Autoencoder in our implementation, though our concept is model-agnostic and can be applied with any suitable counterfactual method. We evaluate our concept on three distinct medical data sets and empirically demonstrate that counterfactual baselines yield more faithful and medically relevant attributions, outperforming standard baseline choices as well as other related methods.

Deep learning offers potential for various healthcare applications, yet requires extensive datasets of curated medical images where data privacy, cost, and distribution mismatch across various acquisition centers could become major problems. To overcome these challenges, we propose a generative adversarial network (SkullGAN) to create large datasets of synthetic skull CT slices, geared towards training models for transcranial ultrasound. With wide ranging applications in treatment of essential tremor, Parkinson's, and Alzheimer's disease, transcranial ultrasound clinical pipelines can be significantly optimized via integration of deep learning. The main roadblock is the lack of sufficient skull CT slices for the purposes of training, which SkullGAN aims to address. Actual CT slices of 38 healthy subjects were used for training. The generated synthetic skull images were then evaluated based on skull density ratio, mean thickness, and mean intensity. Their fidelity was further analyzed using t-distributed stochastic neighbor embedding (t-SNE), Fr\'echet inception distance (FID) score, and visual Turing test (VTT) taken by four staff clinical radiologists. SkullGAN-generated images demonstrated similar quantitative radiological features to real skulls. t-SNE failed to separate real and synthetic samples from one another, and the FID score was 49. Expert radiologists achieved a 60\% mean accuracy on the VTT. SkullGAN makes it possible for researchers to generate large numbers of synthetic skull CT segments, necessary for training neural networks for medical applications involving the human skull, such as transcranial focused ultrasound, mitigating challenges with access, privacy, capital, time, and the need for domain expertise.

Generating samples given a specific label requires estimating conditional distributions. We derive a tractable upper bound of the Wasserstein distance between conditional distributions to lay the theoretical groundwork to learn conditional distributions. Based on this result, we propose a novel conditional generation algorithm where conditional distributions are fully characterized by a metric space defined by a statistical distance. We employ optimal transport theory to propose the Wasserstein geodesic generator, a new conditional generator that learns the Wasserstein geodesic. The proposed method learns both conditional distributions for observed domains and optimal transport maps between them. The conditional distributions given unobserved intermediate domains are on the Wasserstein geodesic between conditional distributions given two observed domain labels. The proposed method generates the Wasserstein geodesic under some conditions. Experiments on face images with light conditions as domain labels demonstrate the efficacy of the proposed method.

Powerful priors allow us to perform inference with insufficient information. In this paper, we propose an autoregressive prior for 3D shapes to solve multimodal 3D tasks such as shape completion, reconstruction, and generation. We model the distribution over 3D shapes as a non-sequential autoregressive distribution over a discretized, low-dimensional, symbolic grid-like latent representation of 3D shapes. This enables us to represent distributions over 3D shapes conditioned on information from an arbitrary set of spatially anchored query locations and thus perform shape completion in such arbitrary settings (e.g., generating a complete chair given only a view of the back leg). We also show that the learned autoregressive prior can be leveraged for conditional tasks such as single-view reconstruction and language-based generation. This is achieved by learning task-specific naive conditionals which can be approximated by light-weight models trained on minimal paired data. We validate the effectiveness of the proposed method using both quantitative and qualitative evaluation and show that the proposed method outperforms the specialized state-of-the-art methods trained for individual tasks. The project page with code and video visualizations can be found at https://yccyenchicheng.github.io/AutoSDF/.

This article presents our generative model for rhythm action games together with applications in business operations. Rhythm action games are video games in which the player is challenged to issue commands at the right timings during a music session. The timings are rendered in the chart, which consists of visual symbols, called notes, flying through the screen. We introduce our deep generative model, Gen\'eLive!, which outperforms the state-of-the-art model by taking into account musical structures through beats and temporal scales. Thanks to its favorable performance, Gen\'eLive! was put into operation at KLab Inc., a Japan-based video game developer, and reduced the business cost of chart generation by as much as half. The application target included the phenomenal "Love Live!," which has more than 10 million users across Asia and beyond, and is one of the few rhythm action franchises that has led the online era of the genre. In this article, we evaluate the generative performance of Gen\'eLive! using production datasets at KLab as well as open datasets for reproducibility, while the model continues to operate in their business. Our code and the model, tuned and trained using a supercomputer, are publicly available.

Neuroevolution is one of the methodologies that can be used for learning optimal architecture during training. It uses evolutionary algorithms to generate the topology of artificial neural networks and its parameters. The main benefits are that it is scalable and can be fully or partially non gradient method. In this work, a modified neuroevolution technique is presented which incorporates multi-level optimisation. The presented approach adapts evolution strategies for evolving an ensemble model based on the bagging technique, using genetic operators for optimising single anomaly detection models, reducing the training dataset to speedup the search process and perform non-gradient fine tuning. Multivariate anomaly detection as an unsupervised learning task is the case study upon which the presented approach is tested. Single model optimisation is based on mutation and crossover operators and is focused on finding optimal window sizes, the number of layers, layer depths, hyperparameters etc. to boost the anomaly detection scores of new and already known models. The proposed framework and its protocol shows that it is possible to find architecture within a reasonable time frame which can boost all well known multivariate anomaly detection deep learning architectures. The work concentrates on improvements to the multi-level neuroevolution approach for anomaly detection. The main modifications are in the methods of mixing groups and single model evolution, non-gradient fine tuning and a voting mechanism. The presented framework can be used as an efficient learning network architecture method for any different unsupervised task where autoencoder architectures can be used. The tests were run on SWAT and WADI datasets and the presented approach evolved the architectures that achieved the best scores among other deep learning models.

In this paper, the bias classifier is introduced, that is, the bias part of a DNN with Relu as the activation function is used as a classifier. The work is motivated by the fact that the bias part is a piecewise constant function with zero gradient and hence cannot be directly attacked by gradient-based methods to generate adversaries such as FGSM. The existence of the bias classifier is proved an effective training method for the bias classifier is proposed. It is proved that by adding a proper random first-degree part to the bias classifier, an information-theoretically safe classifier against the original-model gradient-based attack is obtained in the sense that the attack generates a totally random direction for generating adversaries. This seems to be the first time that the concept of information-theoretically safe classifier is proposed. Several attack methods for the bias classifier are proposed and numerical experiments are used to show that the bias classifier is more robust than DNNs against these attacks in most cases.

In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables. The joint density of a CEBM decomposes into an intractable distribution over data and a tractable posterior over latent variables. CEBMs have similar use cases as variational autoencoders, in the sense that they learn an unsupervised mapping from data to latent variables. However, these models omit a generator network, which allows them to learn more flexible notions of similarity between data points. Our experiments demonstrate that conjugate EBMs achieve competitive results in terms of image modelling, predictive power of latent space, and out-of-domain detection on a variety of datasets.

Capturing the structure of a data-generating process by means of appropriate inductive biases can help in learning models that generalize well and are robust to changes in the input distribution. While methods that harness spatial and temporal structures find broad application, recent work has demonstrated the potential of models that leverage sparse and modular structure using an ensemble of sparingly interacting modules. In this work, we take a step towards dynamic models that are capable of simultaneously exploiting both modular and spatiotemporal structures. We accomplish this by abstracting the modeled dynamical system as a collection of autonomous but sparsely interacting sub-systems. The sub-systems interact according to a topology that is learned, but also informed by the spatial structure of the underlying real-world system. This results in a class of models that are well suited for modeling the dynamics of systems that only offer local views into their state, along with corresponding spatial locations of those views. On the tasks of video prediction from cropped frames and multi-agent world modeling from partial observations in the challenging Starcraft2 domain, we find our models to be more robust to the number of available views and better capable of generalization to novel tasks without additional training, even when compared against strong baselines that perform equally well or better on the training distribution.