SPM Article

In addition to the impressive predictive power of machine learning (ML) models, more recently, explanation methods have emerged that enable an interpretation of complex nonlinear learning models, such as deep neural networks. Gaining a better understanding is especially important, e.g., for safety-critical ML applications or medical diagnostics and so on. Although such explainable artificial intelligence (XAI) techniques have reached significant popularity for classifiers, thus far, little attention has been devoted to XAI for regression models (XAIR). 

In many modern data science problems, data are represented by a graph (network), e.g., social, biological, and communication networks. Over the past decade, numerous signal processing and machine learning (ML) algorithms have been introduced for analyzing graph structured data. With the growth of interest in graphs and graph-based learning tasks in a variety of applications, there is a need to explore explainability in graph data science.

Data-driven solutions are playing an increasingly important role in numerous practical problems across multiple disciplines. The shift from the traditional model-driven approaches to those that are data driven naturally emphasizes the importance of the explainability of solutions, as, in this case, the connection to a physical model is often not obvious. Explainability is a broad umbrella and includes interpretability, but it also implies that the solutions need to be complete, in that one should be able to “audit” them, ask appropriate questions, and hence gain further insight about their inner workings.

Most of the work we do in signal processing these days is data driven. The shift from the more traditional and model-driven approaches to those that are data driven has also underlined the importance of explainability of our solutions. Because most traditional signal processing approaches start with a number of modeling assumptions, they are comprehensible by the very nature of their construction.

Self-supervised representation learning (SSRL) methods aim to provide powerful, deep feature learning without the requirement of large annotated data sets, thus alleviating the annotation bottleneck-one of the main barriers to the practical deployment of deep learning today. These techniques have advanced rapidly in recent years, with their efficacy approaching and sometimes surpassing fully supervised pretraining alternatives across a variety of data modalities, including image, video, sound, text, and graphs.

The dramatic success of deep learning is largely due to the availability of data. Data samples are often acquired on edge devices, such as smartphones, vehicles, and sensors, and in some cases cannot be shared due to privacy considerations. Federated learning is an emerging machine learning paradigm for training models across multiple edge devices holding local data sets, without explicitly exchanging the data. Learning in a federated manner differs from conventional centralized machine learning and poses several core unique challenges and requirements, which are closely related to classical problems studied in the areas of signal processing and communications.

Fire and water, two of nature’s basic forces, are each capable of sustaining or destroying life and property. Research projects in California and Hawaii are, respectively, helping displaced families cope with devasting wildfires, and investigating a way to increase water supply availability on isolated islands. Both projects are relying on signal processing to help them meet their goals.

“Science without conscience is only ruin of the soul” said François Rabelais. This centuries-old quote still resonates, today maybe louder than ever. I began to write this editorial at the end of February when Russian tanks and soldiers invaded Ukraine and waves of bombers began dropping their bombs on Ukrainian cities, targeting civilian buildings, hospitals, and schools. This dramatic event was a shock to Europeans, since most of them have lived in relative peace for more than 70 years.

Robots are rapidly becoming an integral part of daily life. The mechanizing of routine tasks has been underway for decades, with development making particularly remarkable progress over the past several years. Now, with the development robots that can closely interact with humans, sensing users’ needs and often relieving people of dangerous tasks, robotic technology is entering a new phase of intimacy and practicality.