SPM Articles

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.

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.

A window function is a mathematical function that is zero valued outside some chosen interval [1] , [2] . For applications like filtering, detection, and estimation, the window functions take the form of limited time functions, which are in general real and even functions [3] , [4] , while for applications like beamforming and image processing, they are limited spatial functions. A spatial window can be a complex function for optimizing the beams in magnitude as well as in phase, as in the case of certain antenna arrays, where the phasor currents in the array are complex numbers [5].

Multiscale 3D characterization is widely used by materials scientists to further their understanding of the relationships between microscopic structure and macroscopic function. Scientific computed tomography (SCT) instruments are one of the most popular choices for 3D nondestructive characterization of materials at length scales ranging from the angstrom scale to the micron scale. These instruments typically have a source of radiation (such as electrons, X-rays, or neutrons) that interacts with the sample to be studied and a detector assembly to capture the result of this interaction (see Figure 1 ).

The Markov random field (MRF) is one of the most widely used models in image processing, constituting a prior model for addressing problems such as image segmentation, object detection, and reconstruction. What is not often appreciated is that the MRF owes its origin to the physics of solids, making it an ideal prior model for processing microscopic observations of materials. While both fields know of their respective interpretations of the MRF, each knows very little about the other’s version of it. Hence, both fields have “blind spots,” where some concepts readily appreciated by one field are completely obscured from the other. 

Given the increasing prevalence of facial analysis technology, the problem of bias in the tools is now becoming an even greater source of concern. Several studies have highlighted the pervasiveness of such discrimination, and many have sought to address the problem by proposing solutions to mitigate it. Despite this effort, to date, understanding, investigating, and mitigating bias for facial affect analysis remain an understudied problem.

Recent advances in the field of machine learning have shown great potential for the automatic recognition of apparent human emotions. In the era of Internet of Things and big-data processing, where voice-based systems are well established, opportunities to leverage cutting-edge technologies to develop personalized and human-centered services are genuinely real, with a growing demand in many areas such as education, health, well-being, and entertainment. 

Imagine standing on a street corner in the city. With your eyes closed you can hear and recognize a succession of sounds: cars passing by, people speaking, their footsteps when they walk by, and the continuous falling of rain. The recognition of all these sounds and interpretation of the perceived scene as a city street soundscape comes naturally to humans. It is, however, the result of years of "training":