A great interest has arisen in using Deep Generative Models (DGM) for generative design. When assessing the quality of the generated designs, human designers focus more on structural plausibility, e.g., no missing component, rather than visual artifacts, e.g., noises in the images. Meanwhile, commonly used metrics such as Fr\'echet Inception Distance (FID) may not evaluate accurately as they tend to penalize visual artifacts instead of structural implausibility. As such, FID might not be suitable to assess the performance of DGMs for a generative design task. In this work, we propose to encode the input designs with a simple Denoising Autoencoder (DAE) and measure the distribution distance in the latent space thereof. We experimentally test our DAE-based metrics with FID and other state-of-the-art metrics on three data sets: compared to FID and some more recent works, e.g., FD$_\text{DINO-V2}$ and topology distance, DAE-based metrics can effectively detect implausible structures and are more consistent with structural inspection by human experts.
The number of proposed iterative optimization heuristics is growing steadily, and with this growth, there have been many points of discussion within the wider community. One particular criticism that is raised towards many new algorithms is their focus on metaphors used to present the method, rather than emphasizing their potential algorithmic contributions. Several studies into popular metaphor-based algorithms have highlighted these problems, even showcasing algorithms that are functionally equivalent to older existing methods. Unfortunately, this detailed approach is not scalable to the whole set of metaphor-based algorithms. Because of this, we investigate ways in which benchmarking can shed light on these algorithms. To this end, we run a set of 294 algorithm implementations on the BBOB function suite. We investigate how the choice of the budget, the performance measure, or other aspects of experimental design impact the comparison of these algorithms. Our results emphasize why benchmarking is a key step in expanding our understanding of the algorithm space, and what challenges still need to be overcome to fully gauge the potential improvements to the state-of-the-art hiding behind the metaphors.
Although Deep Reinforcement Learning (DRL) methods can learn effective policies for challenging problems such as Atari games and robotics tasks, algorithms are complex and training times are often long. This study investigates how evolution strategies (ES) perform compared to gradient-based deep reinforcement learning methods. We use ES to optimize the weights of a neural network via neuroevolution, performing direct policy search. We benchmark both regular networks and policy networks consisting of a single linear layer from observations to actions; for three classical ES methods and for three gradient-based methods such as PPO. Our results reveal that ES can find effective linear policies for many RL benchmark tasks, in contrast to DRL methods that can only find successful policies using much larger networks, suggesting that current benchmarks are easier to solve than previously assumed. Interestingly, also for higher complexity tasks, ES achieves results comparable to gradient-based DRL algorithms. Furthermore, we find that by directly accessing the memory state of the game, ES are able to find successful policies in Atari, outperforming DQN. While gradient-based methods have dominated the field in recent years, ES offers an alternative that is easy to implement, parallelize, understand, and tune.
Symbolic regression (SR) poses a significant challenge for randomized search heuristics due to its reliance on the synthesis of expressions for input-output mappings. Although traditional genetic programming (GP) algorithms have achieved success in various domains, they exhibit limited performance when tree-based representations are used for SR. To address these limitations, we introduce a novel SR approach called Fourier Tree Growing (FTG) that draws insights from functional analysis. This new perspective enables us to perform optimization directly in a different space, thus avoiding intricate symbolic expressions. Our proposed algorithm exhibits significant performance improvements over traditional GP methods on a range of classical one-dimensional benchmarking problems. To identify and explain limiting factors of GP and FTG, we perform experiments on a large-scale polynomials benchmark with high-order polynomials up to degree 100. To the best of the authors' knowledge, this work represents the pioneering application of functional analysis in addressing SR problems. The superior performance of the proposed algorithm and insights into the limitations of GP open the way for further advancing GP for SR and related areas of explainable machine learning.
In this work, we propose a model-agnostic instance-based post-hoc explainability method for time series classification. The proposed algorithm, namely Time-CF, leverages shapelets and TimeGAN to provide counterfactual explanations for arbitrary time series classifiers. We validate the proposed method on several real-world univariate time series classification tasks from the UCR Time Series Archive. The results indicate that the counterfactual instances generated by Time-CF when compared to state-of-the-art methods, demonstrate better performance in terms of four explainability metrics: closeness, sensibility, plausibility, and sparsity.
Benchmarking heuristic algorithms is vital to understand under which conditions and on what kind of problems certain algorithms perform well. In most current research into heuristic optimization algorithms, only a very limited number of scenarios, algorithm configurations and hyper-parameter settings are explored, leading to incomplete and often biased insights and results. This paper presents a novel approach we call explainable benchmarking. Introducing the IOH-Xplainer software framework, for analyzing and understanding the performance of various optimization algorithms and the impact of their different components and hyper-parameters. We showcase the framework in the context of two modular optimization frameworks. Through this framework, we examine the impact of different algorithmic components and configurations, offering insights into their performance across diverse scenarios. We provide a systematic method for evaluating and interpreting the behaviour and efficiency of iterative optimization heuristics in a more transparent and comprehensible manner, allowing for better benchmarking and algorithm design.
Choosing a set of benchmark problems is often a key component of any empirical evaluation of iterative optimization heuristics. In continuous, single-objective optimization, several sets of problems have become widespread, including the well-established BBOB suite. While this suite is designed to enable rigorous benchmarking, it is also commonly used for testing methods such as algorithm selection, which the suite was never designed around. We present the MA-BBOB function generator, which uses the BBOB suite as component functions in an affine combination. In this work, we describe the full procedure to create these affine combinations and highlight the trade-offs of several design decisions, specifically the choice to place the optimum uniformly at random in the domain. We then illustrate how this generator can be used to gain more low-level insight into the function landscapes through the use of exploratory landscape analysis. Finally, we show a potential use-case of MA-BBOB in generating a wide set of training and testing data for algorithm selectors. Using this setup, we show that the basic scheme of using a set of landscape features to predict the best algorithm does not lead to optimal results, and that an algorithm selector trained purely on the BBOB functions generalizes poorly to the affine combinations.
Deep Generative Models (DGMs) are widely used to create innovative designs across multiple industries, ranging from fashion to the automotive sector. In addition to generating images of high visual quality, the task of structural design generation imposes more stringent constrains on the semantic expression, e.g., no floating material or missing part, which we refer to as plausibility in this work. We delve into the impact of noise schedules of diffusion models on the plausibility of the outcome: there exists a range of noise levels at which the model's performance decides the result plausibility. Also, we propose two techniques to determine such a range for a given image set and devise a novel parametric noise schedule for better plausibility. We apply this noise schedule to the training and sampling of the well-known diffusion model EDM and compare it to its default noise schedule. Compared to EDM, our schedule significantly improves the rate of plausible designs from 83.4% to 93.5% and Fr\'echet Inception Distance (FID) from 7.84 to 4.87. Further applications of advanced image editing tools demonstrate the model's solid understanding of structure.
A clear need for automatic anomaly detection applied to automotive testing has emerged as more and more attention is paid to the data recorded and manual evaluation by humans reaches its capacity. Such real-world data is massive, diverse, multivariate and temporal in nature, therefore requiring modelling of the testee behaviour. We propose a variational autoencoder with multi-head attention (MA-VAE), which, when trained on unlabelled data, not only provides very few false positives but also manages to detect the majority of the anomalies presented. In addition to that, the approach offers a novel way to avoid the bypass phenomenon, an undesirable behaviour investigated in literature. Lastly, the approach also introduces a new method to remap individual windows to a continuous time series. The results are presented in the context of a real-world industrial data set and several experiments are undertaken to further investigate certain aspects of the proposed model. When configured properly, it is 9% of the time wrong when an anomaly is flagged and discovers 67% of the anomalies present. Also, MA-VAE has the potential to perform well with only a fraction of the training and validation subset, however, to extract it, a more sophisticated threshold estimation method is required.
Generative Engineering Design approaches driven by Deep Generative Models (DGM) have been proposed to facilitate industrial engineering processes. In such processes, designs often come in the form of images, such as blueprints, engineering drawings, and CAD models depending on the level of detail. DGMs have been successfully employed for synthesis of natural images, e.g., displaying animals, human faces and landscapes. However, industrial design images are fundamentally different from natural scenes in that they contain rich structural patterns and long-range dependencies, which are challenging for convolution-based DGMs to generate. Moreover, DGM-driven generation process is typically triggered based on random noisy inputs, which outputs unpredictable samples and thus cannot perform an efficient industrial design exploration. We tackle these challenges by proposing a novel model Self-Attention Adversarial Latent Autoencoder (SA-ALAE), which allows generating feasible design images of complex engineering parts. With SA-ALAE, users can not only explore novel variants of an existing design, but also control the generation process by operating in latent space. The potential of SA-ALAE is shown by generating engineering blueprints in a real automotive design task.