Saliency Maps are Ambiguous: Analysis of Logical Relations on First and Second Order Attributions

Recent work uncovered potential flaws in \eg attribution or heatmap based saliency methods. A typical flaw is a confirmations bias, where the scores are compared to human expectation. Since measuring the quality of saliency methods is hard due to missing ground truth model reasoning, finding general limitations is also hard. This is further complicated, because masking-based evaluation on complex data can easily introduce a bias, as most methods cannot fully ignore inputs. In this work, we extend our previous analysis on the logical dataset framework ANDOR, where we showed that all analysed saliency methods fail to grasp all needed classification information for all possible scenarios. Specifically, this paper extends our previous work using analysis on more datasets, in order to better understand in which scenarios the saliency methods fail. Further, we apply the Global Coherence Representation as an additional evaluation method in order to enable actual input omission.

Saliency Methods are Encoders: Analysing Logical Relations Towards Interpretation

With their increase in performance, neural network architectures also become more complex, necessitating explainability. Therefore, many new and improved methods are currently emerging, which often generate so-called saliency maps in order to improve interpretability. Those methods are often evaluated by visual expectations, yet this typically leads towards a confirmation bias. Due to a lack of a general metric for explanation quality, non-accessible ground truth data about the model's reasoning and the large amount of involved assumptions, multiple works claim to find flaws in those methods. However, this often leads to unfair comparison metrics. Additionally, the complexity of most datasets (mostly images or text) is often so high, that approximating all possible explanations is not feasible. For those reasons, this paper introduces a test for saliency map evaluation: proposing controlled experiments based on all possible model reasonings over multiple simple logical datasets. Using the contained logical relationships, we aim to understand how different saliency methods treat information in different class discriminative scenarios (e.g. via complementary and redundant information). By introducing multiple new metrics, we analyse propositional logical patterns towards a non-informative attribution score baseline to find deviations of typical expectations. Our results show that saliency methods can encode classification relevant information into the ordering of saliency scores.

Knowledge-Augmented Explainable and Interpretable Learning for Anomaly Detection and Diagnosis

Knowledge-augmented learning enables the combination of knowledge-based and data-driven approaches. For anomaly detection and diagnosis, understandability is typically an important factor, especially in high-risk areas. Therefore, explainability and interpretability are also major criteria in such contexts. This chapter focuses on knowledge-augmented explainable and interpretable learning to enhance understandability, transparency and ultimately computational sensemaking. We exemplify different approaches and methods in the domains of anomaly detection and diagnosis - from comparatively simple interpretable methods towards more advanced neuro-symbolic approaches.

Online Knowledge Integration for 3D Semantic Mapping: A Survey

Semantic mapping is a key component of robots operating in and interacting with objects in structured environments. Traditionally, geometric and knowledge representations within a semantic map have only been loosely integrated. However, recent advances in deep learning now allow full integration of prior knowledge, represented as knowledge graphs or language concepts, into sensor data processing and semantic mapping pipelines. Semantic scene graphs and language models enable modern semantic mapping approaches to incorporate graph-based prior knowledge or to leverage the rich information in human language both during and after the mapping process. This has sparked substantial advances in semantic mapping, leading to previously impossible novel applications. This survey reviews these recent developments comprehensively, with a focus on online integration of knowledge into semantic mapping. We specifically focus on methods using semantic scene graphs for integrating symbolic prior knowledge and language models for respective capture of implicit common-sense knowledge and natural language concepts

Tailoring the Hyperparameters of a Wide-Kernel Convolutional Neural Network to Fit Different Bearing Fault Vibration Datasets

State-of-the-art algorithms are reported to be almost perfect at distinguishing the vibrations arising from healthy and damaged machine bearings, according to benchmark datasets at least. However, what about their application to new data? In this paper, we are able to confirm that neural networks for bearing fault detection can be crippled by incorrect hyperparameterisation, and also that the correct hyperparameter settings can actually change when transitioning to new data. The paper weaves together multiple methods to explain the behaviour of the hyperparameters of a wide-kernel convolutional neural network and how to set them. Since guidance already exists for generic hyperparameters like minibatch size, we focus on how to set architecture-specific hyperparameters such as the width of the convolutional kernels, a topic which might otherwise be obscure. We reflect different data properties by fusing information from seven different benchmark datasets, and our results show that the kernel size in the first layer in particular is sensitive to changes in the data. Looking deeper, we use manipulated copies of one dataset in an attempt to spot why the kernel size sometimes needs to change. The relevance of sampling rate is studied by using different levels of resampling, and spectral content is studied by increasingly filtering out high frequencies. At the end of our paper we conclude by stating clear guidance on how to set the hyperparameters of our neural network architecture.

An Efficient Model-Agnostic Approach for Uncertainty Estimation in Data-Restricted Pedometric Applications

This paper introduces a model-agnostic approach designed to enhance uncertainty estimation in the predictive modeling of soil properties, a crucial factor for advancing pedometrics and the practice of digital soil mapping. For addressing the typical challenge of data scarcity in soil studies, we present an improved technique for uncertainty estimation. This method is based on the transformation of regression tasks into classification problems, which not only allows for the production of reliable uncertainty estimates but also enables the application of established machine learning algorithms with competitive performance that have not yet been utilized in pedometrics. Empirical results from datasets collected from two German agricultural fields showcase the practical application of the proposed methodology. Our results and findings suggest that the proposed approach has the potential to provide better uncertainty estimation than the models commonly used in pedometrics.

Improving Nonlinear Projection Heads using Pretrained Autoencoder Embeddings

This empirical study aims at improving the effectiveness of the standard 2-layer MLP projection head $g(\cdot)$ featured in the SimCLR framework through the use of pretrained autoencoder embeddings. Given a contrastive learning task with a largely unlabeled image classification dataset, we first train a shallow autoencoder architecture and extract its compressed representations contained in the encoder's embedding layer. After freezing the weights within this pretrained layer, we use it as a drop-in replacement for the input layer of SimCLR's default projector. Additionally, we also apply further architectural changes to the projector by decreasing its width and changing its activation function. The different projection heads are then used to contrastively train and evaluate a feature extractor $f(\cdot)$ following the SimCLR protocol, while also examining the performance impact of Z-score normalized datasets. Our experiments indicate that using a pretrained autoencoder embedding in the projector can not only increase classification accuracy by up to 2.9% or 1.7% on average but can also significantly decrease the dimensionality of the projection space. Our results also suggest, that using the sigmoid and tanh activation functions within the projector can outperform ReLU in terms of peak and average classification accuracy. When applying our presented projectors, then not applying Z-score normalization to datasets often increases peak performance. In contrast, the default projection head can benefit more from normalization. All experiments involving our pretrained projectors are conducted with frozen embeddings, since our test results indicate an advantage compared to using their non-frozen counterparts.

Multivariate Time Series Regression with Graph Neural Networks

Machine learning, with its advances in Deep Learning has shown great potential in analysing time series in the past. However, in many scenarios, additional information is available that can potentially improve predictions, by incorporating it into the learning methods. This is crucial for data that arises from e.g., sensor networks that contain information about sensor locations. Then, such spatial information can be exploited by modeling it via graph structures, along with the sequential (time) information. Recent advances in adapting Deep Learning to graphs have shown promising potential in various graph-related tasks. However, these methods have not been adapted for time series related tasks to a great extent. Specifically, most attempts have essentially consolidated around Spatial-Temporal Graph Neural Networks for time series forecasting with small sequence lengths. Generally, these architectures are not suited for regression or classification tasks that contain large sequences of data. Therefore, in this work, we propose an architecture capable of processing these long sequences in a multivariate time series regression task, using the benefits of Graph Neural Networks to improve predictions. Our model is tested on two seismic datasets that contain earthquake waveforms, where the goal is to predict intensity measurements of ground shaking at a set of stations. Our findings demonstrate promising results of our approach, which are discussed in depth with an additional ablation study.

Local Exceptionality Detection in Time Series Using Subgroup Discovery

In this paper, we present a novel approach for local exceptionality detection on time series data. This method provides the ability to discover interpretable patterns in the data, which can be used to understand and predict the progression of a time series. This being an exploratory approach, the results can be used to generate hypotheses about the relationships between the variables describing a specific process and its dynamics. We detail our approach in a concrete instantiation and exemplary implementation, specifically in the field of teamwork research. Using a real-world dataset of team interactions we include results from an example data analytics application of our proposed approach, showcase novel analysis options, and discuss possible implications of the results from the perspective of teamwork research.

A Computational Framework for Modeling Complex Sensor Network Data Using Graph Signal Processing and Graph Neural Networks in Structural Health Monitoring

Complex networks lend themselves to the modeling of multidimensional data, such as relational and/or temporal data. In particular, when such complex data and their inherent relationships need to be formalized, complex network modeling and its resulting graph representations enable a wide range of powerful options. In this paper, we target this - connected to specific machine learning approaches on graphs for structural health monitoring on an analysis and predictive (maintenance) perspective. Specifically, we present a framework based on Complex Network Modeling, integrating Graph Signal Processing (GSP) and Graph Neural Network (GNN) approaches. We demonstrate this framework in our targeted application domain of Structural Health Monitoring (SHM). In particular, we focus on a prominent real-world structural health monitoring use case, i.e., modeling and analyzing sensor data (strain, vibration) of a large bridge in the Netherlands. In our experiments, we show that GSP enables the identification of the most important sensors, for which we investigate a set of search and optimization approaches. Furthermore, GSP enables the detection of specific graph signal patterns (mode shapes), capturing physical functional properties of the sensors in the applied complex network. In addition, we show the efficacy of applying GNNs for strain prediction on this kind of data.