Process mining on business process execution data has focused primarily on orchestration-type processes performed in a single organization (intra-organizational). Collaborative (inter-organizational) processes, unlike those of orchestration type, expand several organizations (for example, in e-Government), adding complexity and various challenges both for their implementation and for their discovery, prediction, and analysis of their execution. Predictive process monitoring is based on exploiting execution data from past instances to predict the execution of current cases. It is possible to make predictions on the next activity and remaining time, among others, to anticipate possible deviations, violations, and delays in the processes to take preventive measures (e.g., re-allocation of resources). In this work, we propose an extension for collaborative processes of traditional process prediction, considering particularities of this type of process, which add information of interest in this context, for example, the next activity of which participant or the following message to be exchanged between two participants.

During multimodal model training and reasoning, data samples may miss certain modalities and lead to compromised model performance due to sensor limitations, cost constraints, privacy concerns, data loss, and temporal and spatial factors. This survey provides an overview of recent progress in Multimodal Learning with Missing Modality (MLMM), focusing on deep learning techniques. It is the first comprehensive survey that covers the historical background and the distinction between MLMM and standard multimodal learning setups, followed by a detailed analysis of current MLMM methods, applications, and datasets, concluding with a discussion about challenges and potential future directions in the field.

We examine the abilities of intrinsic bias metrics of static word embeddings to predict whether Natural Language Processing (NLP) systems exhibit biased behavior. A word embedding is one of the fundamental NLP technologies that represents the meanings of words through real vectors, and problematically, it also learns social biases such as stereotypes. An intrinsic bias metric measures bias by examining a characteristic of vectors, while an extrinsic bias metric checks whether an NLP system trained with a word embedding is biased. A previous study found that a common intrinsic bias metric usually does not correlate with extrinsic bias metrics. However, the intrinsic and extrinsic bias metrics did not measure the same bias in most cases, which makes us question whether the lack of correlation is genuine. In this paper, we extract characteristic words from datasets of extrinsic bias metrics and analyze correlations with intrinsic bias metrics with those words to ensure both metrics measure the same bias. We observed moderate to high correlations with some extrinsic bias metrics but little to no correlations with the others. This result suggests that intrinsic bias metrics can predict biased behavior in particular settings but not in others. Experiment codes are available at GitHub.

This fusion can increase efficiency, enhance safety, and improve passenger experience. AI in aviation currently focuses on AI-for-Cabin and non-critical tasks. On the other hand, AI-for-non-Cabin tasks encompass artificial intelligence techniques for the operation of the aircraft, for example, vehicle management or flight control/guidance/management system functions. AI-for-non-Cabin tasks are therefore subject to stringent certification requirements and a thorough and explainable understanding of the target tasks and AI methods to ensure the safety of passengers, flight crew, and aircraft. Moreover, the scope of AI-for-non-Cabin tasks ranges from communication, radar, digital electronics, integrated avionics systems, and navigation, to advanced traffic detection systems, all being considered critical tasks.

Machine learning models make mistakes, yet sometimes it is difficult to identify the systematic problems behind the mistakes. Practitioners engage in various activities, including error analysis, testing, auditing, and red-teaming, to form hypotheses of what can go (or has gone) wrong with their models. To validate these hypotheses, practitioners employ data slicing to identify relevant examples. However, traditional data slicing is limited by available features and programmatic slicing functions. In this work, we propose SemSlicer, a framework that supports semantic data slicing, which identifies a semantically coherent slice, without the need for existing features. SemSlicer uses Large Language Models to annotate datasets and generate slices from any user-defined slicing criteria. We show that SemSlicer generates accurate slices with low cost, allows flexible trade-offs between different design dimensions, reliably identifies under-performing data slices, and helps practitioners identify useful data slices that reflect systematic problems.

We take the perspective in which we want to design a downstream task (such as estimating vegetation coverage) on a certain area of interest (AOI) with a limited labeling budget. By leveraging an existing Foundation Model (FM) we must decide whether we train a downstream model on a different but label-rich AOI hoping it generalizes to our AOI, or we split labels in our AOI for training and validating. In either case, we face choices concerning what FM to use, how to sample our AOI for labeling, etc. which affect both the performance and uncertainty of the results. In this work, we perform a large ablative study using eight existing FMs on either Sentinel 1 or Sentinel 2 as input data, and the classes from the ESA World Cover product as downstream tasks across eleven AOIs. We do repeated sampling and training, resulting in an ablation of some 500K simple linear regression models. Our results show both the limits of spatial generalizability across AOIs and the power of FMs where we are able to get over 0.9 correlation coefficient between predictions and targets on different chip level predictive tasks. And still, performance and uncertainty vary greatly across AOIs, tasks and FMs. We believe this is a key issue in practice, because there are many design decisions behind each FM and downstream task (input modalities, sampling, architectures, pretraining, etc.) and usually a downstream task designer is aware of and can decide upon a few of them. Through this work, we advocate for the usage of the methodology herein described (large ablations on reference global labels and simple probes), both when publishing new FMs, and to make informed decisions when designing downstream tasks to use them.

Graph learning is the fundamental task of estimating unknown graph connectivity from available data. Typical approaches assume that not only is all information available simultaneously but also that all nodes can be observed. However, in many real-world scenarios, data can neither be known completely nor obtained all at once. We present a novel method for online graph estimation that accounts for the presence of hidden nodes. We consider signals that are stationary on the underlying graph, which provides a model for the unknown connections to hidden nodes. We then formulate a convex optimization problem for graph learning from streaming, incomplete graph signals. We solve the proposed problem through an efficient proximal gradient algorithm that can run in real-time as data arrives sequentially. Additionally, we provide theoretical conditions under which our online algorithm is similar to batch-wise solutions. Through experimental results on synthetic and real-world data, we demonstrate the viability of our approach for online graph learning in the presence of missing observations.

Direct speech translation (ST) models often struggle with rare words. Incorrect translation of these words can have severe consequences, impacting translation quality and user trust. While rare word translation is inherently challenging for neural models due to sparse learning signals, real-world scenarios often allow access to translations of past recordings on similar topics. To leverage these valuable resources, we propose a retrieval-and-demonstration approach to enhance rare word translation accuracy in direct ST models. First, we adapt existing ST models to incorporate retrieved examples for rare word translation, which allows the model to benefit from prepended examples, similar to in-context learning. We then develop a cross-modal (speech-to-speech, speech-to-text, text-to-text) retriever to locate suitable examples. We demonstrate that standard ST models can be effectively adapted to leverage examples for rare word translation, improving rare word translation accuracy over the baseline by 17.6% with gold examples and 8.5% with retrieved examples. Moreover, our speech-to-speech retrieval approach outperforms other modalities and exhibits higher robustness to unseen speakers. Our code is publicly available (https://github.com/SiqiLii/Retrieve-and-Demonstration-ST).

Rigorous and reproducible evaluation is critical for assessing the state of the art and for guiding scientific advances in Artificial Intelligence. Evaluation is challenging in practice due to several reasons, including benchmark saturation, lack of transparency in methods used for measurement, development challenges in extracting measurements for generative tasks, and, more generally, the extensive number of capabilities required for a well-rounded comparison across models. We make three contributions to alleviate the above challenges. First, we present Eureka, an open-source framework for standardizing evaluations of large foundation models beyond single-score reporting and rankings. Second, we introduce Eureka-Bench as an extensible collection of benchmarks testing capabilities that (i) are still challenging for state-of-the-art models and (ii) represent fundamental but overlooked language and multimodal capabilities. The inherent space for improvement in non-saturated benchmarks enables us to discover meaningful differences between models at a capability level. Third, using Eureka, we conduct an analysis of 12 state-of-the-art models, providing in-depth insights into failure understanding and model comparison, which can be leveraged to plan targeted improvements. In contrast to recent trends in reports and leaderboards showing absolute rankings and claims for one model or another to be the best, our analysis shows that there is no such best model. Different models have different strengths, but there are models that appear more often than others as best performers for some capabilities. Despite the recent improvements, current models still struggle with several fundamental capabilities including detailed image understanding, benefiting from multimodal input when available rather than fully relying on language, factuality and grounding for information retrieval, and over refusals.

The complex nature of disease mechanisms and the variability of patient symptoms present significant obstacles in developing effective diagnostic tools. Although machine learning has made considerable advances in medical diagnosis, its decision-making processes frequently lack transparency, which can jeopardize patient outcomes. This underscores the critical need for Explainable AI (XAI), which not only offers greater clarity but also has the potential to significantly improve patient care. In this literature review, we conduct a detailed analysis of analyzing XAI methods identified through searches across various databases, focusing on chronic conditions such as Parkinson's, stroke, depression, cancer, heart disease, and Alzheimer's disease. The literature search revealed the application of 9 trending XAI algorithms in the field of healthcare and highlighted the pros and cons of each of them. Thus, the article is concluded with a critical appraisal of the challenges and future research opportunities for XAI in human health monitoring.