ICE-T: A Multi-Faceted Concept for Teaching Machine Learning

The topics of Artificial intelligence (AI) and especially Machine Learning (ML) are increasingly making their way into educational curricula. To facilitate the access for students, a variety of platforms, visual tools, and digital games are already being used to introduce ML concepts and strengthen the understanding of how AI works. We take a look at didactic principles that are employed for teaching computer science, define criteria, and, based on those, evaluate a selection of prominent existing platforms, tools, and games. Additionally, we criticize the approach of portraying ML mostly as a black-box and the resulting missing focus on creating an understanding of data, algorithms, and models that come with it. To tackle this issue, we present a concept that covers intermodal transfer, computational and explanatory thinking, ICE-T, as an extension of known didactic principles. With our multi-faceted concept, we believe that planners of learning units, creators of learning platforms and educators can improve on teaching ML.

Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph

The ability of message-passing neural networks (MPNNs) to fit complex functions over graphs is limited each iteration of message-passing over a simple makes representations more similar, a phenomenon known as rank collapse, and over-smoothing as a special case. Most approaches to mitigate over-smoothing extend common message-passing schemes, e.g., the graph convolutional network, by utilizing residual connections, gating mechanisms, normalization, or regularization techniques. Our work contrarily proposes to directly tackle the cause of this issue by modifying the message-passing scheme and exchanging different types of messages using multi-relational graphs. We identify the necessary and sufficient condition to ensure linearly independent node representations. As one instantion, we show that operating on multiple directed acyclic graphs always satisfies our condition and propose to obtain these by defining a strict partial ordering of the nodes. We conduct comprehensive experiments that confirm the benefits of operating on multi-relational graphs to achieve more informative node representations.

AALF: Almost Always Linear Forecasting

Recent works for time-series forecasting more and more leverage the high predictive power of Deep Learning models. With this increase in model complexity, however, comes a lack in understanding of the underlying model decision process, which is problematic for high-stakes decision making. At the same time, simple, interpretable forecasting methods such as Linear Models can still perform very well, sometimes on-par, with Deep Learning approaches. We argue that simple models are good enough most of the time, and forecasting performance can be improved by choosing a Deep Learning method only for certain predictions, increasing the overall interpretability of the forecasting process. In this context, we propose a novel online model selection framework which uses meta-learning to identify these predictions and only rarely uses a non-interpretable, large model. An extensive empirical study on various real-world datasets shows that our selection methodology outperforms state-of-the-art online model selections methods in most cases. We find that almost always choosing a simple Linear Model for forecasting results in competitive performance, suggesting that the need for opaque black-box models in time-series forecasting is smaller than recent works would suggest.

Enhancing Safety for Autonomous Agents in Partly Concealed Urban Traffic Environments Through Representation-Based Shielding

Navigating unsignalized intersections in urban environments poses a complex challenge for self-driving vehicles, where issues such as view obstructions, unpredictable pedestrian crossings, and diverse traffic participants demand a great focus on crash prevention. In this paper, we propose a novel state representation for Reinforcement Learning (RL) agents centered around the information perceivable by an autonomous agent, enabling the safe navigation of previously uncharted road maps. Our approach surpasses several baseline models by a sig nificant margin in terms of safety and energy consumption metrics. These improvements are achieved while maintaining a competitive average travel speed. Our findings pave the way for more robust and reliable autonomous navigation strategies, promising safer and more efficient urban traffic environments.

Using Petri Nets as an Integrated Constraint Mechanism for Reinforcement Learning Tasks

The lack of trust in algorithms is usually an issue when using Reinforcement Learning (RL) agents for control in real-world domains such as production plants, autonomous vehicles, or traffic-related infrastructure, partly due to the lack of verifiability of the model itself. In such scenarios, Petri nets (PNs) are often available for flowcharts or process steps, as they are versatile and standardized. In order to facilitate integration of RL models and as a step towards increasing AI trustworthiness, we propose an approach that uses PNs with three main advantages over typical RL approaches: Firstly, the agent can now easily be modeled with a combined state including both external environmental observations and agent-specific state information from a given PN. Secondly, we can enforce constraints for state-dependent actions through the inherent PN model. And lastly, we can increase trustworthiness by verifying PN properties through techniques such as model checking. We test our approach on a typical four-way intersection traffic light control setting and present our results, beating cycle-based baselines.

Distilling Influences to Mitigate Prediction Churn in Graph Neural Networks

Models with similar performances exhibit significant disagreement in the predictions of individual samples, referred to as prediction churn. Our work explores this phenomenon in graph neural networks by investigating differences between models differing only in their initializations in their utilized features for predictions. We propose a novel metric called Influence Difference (ID) to quantify the variation in reasons used by nodes across models by comparing their influence distribution. Additionally, we consider the differences between nodes with a stable and an unstable prediction, positing that both equally utilize different reasons and thus provide a meaningful gradient signal to closely match two models even when the predictions for nodes are similar. Based on our analysis, we propose to minimize this ID in Knowledge Distillation, a domain where a new model should closely match an established one. As an efficient approximation, we introduce DropDistillation (DD) that matches the output for a graph perturbed by edge deletions. Our empirical evaluation of six benchmark datasets for node classification validates the differences in utilized features. DD outperforms previous methods regarding prediction stability and overall performance in all considered Knowledge Distillation experiments.

Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks

Our study reveals new theoretical insights into over-smoothing and feature over-correlation in deep graph neural networks. We show the prevalence of invariant subspaces, demonstrating a fixed relative behavior that is unaffected by feature transformations. Our work clarifies recent observations related to convergence to a constant state and a potential over-separation of node states, as the amplification of subspaces only depends on the spectrum of the aggregation function. In linear scenarios, this leads to node representations being dominated by a low-dimensional subspace with an asymptotic convergence rate independent of the feature transformations. This causes a rank collapse of the node representations, resulting in over-smoothing when smooth vectors span this subspace, and over-correlation even when over-smoothing is avoided. Guided by our theory, we propose a sum of Kronecker products as a beneficial property that can provably prevent over-smoothing, over-correlation, and rank collapse. We empirically extend our insights to the non-linear case, demonstrating the inability of existing models to capture linearly independent features.

Curvature-based Pooling within Graph Neural Networks

Over-squashing and over-smoothing are two critical issues, that limit the capabilities of graph neural networks (GNNs). While over-smoothing eliminates the differences between nodes making them indistinguishable, over-squashing refers to the inability of GNNs to propagate information over long distances, as exponentially many node states are squashed into fixed-size representations. Both phenomena share similar causes, as both are largely induced by the graph topology. To mitigate these problems in graph classification tasks, we propose CurvPool, a novel pooling method. CurvPool exploits the notion of curvature of a graph to adaptively identify structures responsible for both over-smoothing and over-squashing. By clustering nodes based on the Balanced Forman curvature, CurvPool constructs a graph with a more suitable structure, allowing deeper models and the combination of distant information. We compare it to other state-of-the-art pooling approaches and establish its competitiveness in terms of classification accuracy, computational complexity, and flexibility. CurvPool outperforms several comparable methods across all considered tasks. The most consistent results are achieved by pooling densely connected clusters using the sum aggregation, as this allows additional information about the size of each pool.

Distributed LSTM-Learning from Differentially Private Label Proportions

Data privacy and decentralised data collection has become more and more popular in recent years. In order to solve issues with privacy, communication bandwidth and learning from spatio-temporal data, we will propose two efficient models which use Differential Privacy and decentralized LSTM-Learning: One, in which a Long Short Term Memory (LSTM) model is learned for extracting local temporal node constraints and feeding them into a Dense-Layer (LabelProportionToLocal). The other approach extends the first one by fetching histogram data from the neighbors and joining the information with the LSTM output (LabelProportionToDense). For evaluation two popular datasets are used: Pems-Bay and METR-LA. Additionally, we provide an own dataset, which is based on LuST. The evaluation will show the tradeoff between performance and data privacy.

LOSDD: Leave-Out Support Vector Data Description for Outlier Detection

Support Vector Machines have been successfully used for one-class classification (OCSVM, SVDD) when trained on clean data, but they work much worse on dirty data: outliers present in the training data tend to become support vectors, and are hence considered "normal". In this article, we improve the effectiveness to detect outliers in dirty training data with a leave-out strategy: by temporarily omitting one candidate at a time, this point can be judged using the remaining data only. We show that this is more effective at scoring the outlierness of points than using the slack term of existing SVM-based approaches. Identified outliers can then be removed from the data, such that outliers hidden by other outliers can be identified, to reduce the problem of masking. Naively, this approach would require training N individual SVMs (and training $O(N^2)$ SVMs when iteratively removing the worst outliers one at a time), which is prohibitively expensive. We will discuss that only support vectors need to be considered in each step and that by reusing SVM parameters and weights, this incremental retraining can be accelerated substantially. By removing candidates in batches, we can further improve the processing time, although it obviously remains more costly than training a single SVM.