When making strategic decisions, we are often confronted with overwhelming information to process. The situation can be further complicated when some pieces of evidence are contradicted each other or paradoxical. The challenge then becomes how to determine which information is useful and which ones should be eliminated. This process is known as meta-decision. Likewise, when it comes to using Artificial Intelligence (AI) systems for strategic decision-making, placing trust in the AI itself becomes a meta-decision, given that many AI systems are viewed as opaque "black boxes" that process large amounts of data. Trusting an opaque system involves deciding on the level of Trustworthy AI (TAI). We propose a new approach to address this issue by introducing a novel taxonomy or framework of TAI, which encompasses three crucial domains: articulate, authentic, and basic for different levels of trust. To underpin these domains, we create ten dimensions to measure trust: explainability/transparency, fairness/diversity, generalizability, privacy, data governance, safety/robustness, accountability, reproducibility, reliability, and sustainability. We aim to use this taxonomy to conduct a comprehensive survey and explore different TAI approaches from a strategic decision-making perspective.

Matching games naturally generalize assignment games, a well-known class of cooperative games. Interest in matching games has grown recently due to some breakthrough results and new applications. This state-of-the-art survey provides an overview of matching games and extensions, such as b-matching games and partitioned matching games; the latter originating from the emerging area of international kidney exchange. In this survey we focus on computational complexity aspects of various game-theoretical solution concepts, such as the core, nucleolus and Shapley value, when the input is restricted to a matching game or one of its variants.

Automated machine learning (AutoML) strives for the automatic configuration of machine learning algorithms and their composition into an overall (software) solution — a machine learning pipeline — tailored to the learning task (dataset) at hand. Over the last decade, AutoML has developed into an independent research field with hundreds of contributions. At the same time, AutoML is being criticized for its high resource consumption as many approaches rely on the (costly) evaluation of many machine learning pipelines, as well as the expensive large-scale experiments across many datasets and approaches. In the spirit of recent work on Green AI, this paper proposes Green AutoML, a paradigm to make the whole AutoML process more environmentally friendly. Therefore, we first elaborate on how to quantify the environmental footprint of an AutoML tool. Afterward, different strategies on how to design and benchmark an AutoML tool w.r.t. their “greenness”, i.e., sustainability, are summarized. Finally, we elaborate on how to be transparent about the environmental footprint and what kind of research incentives could direct the community in a more sustainable AutoML research direction. As part of this, we propose a sustainability checklist to be attached to every AutoML paper featuring all core aspects of Green AutoML.

In recent years, large language models (e.g., Open AI's GPT-4, Meta's LLaMa, Google's PaLM) have become the dominant approach for building AI systems to analyze and generate language online. However, the automated systems that increasingly mediate our interactions online -- such as chatbots, content moderation systems, and search engines -- are primarily designed for and work far more effectively in English than in the world's other 7,000 languages. Recently, researchers and technology companies have attempted to extend the capabilities of large language models into languages other than English by building what are called multilingual language models. In this paper, we explain how these multilingual language models work and explore their capabilities and limits. Part I provides a simple technical explanation of how large language models work, why there is a gap in available data between English and other languages, and how multilingual language models attempt to bridge that gap. Part II accounts for the challenges of doing content analysis with large language models in general and multilingual language models in particular. Part III offers recommendations for companies, researchers, and policymakers to keep in mind when considering researching, developing and deploying large and multilingual language models.

Cross-lingual Machine Translation (MT) quality estimation plays a crucial role in evaluating translation performance. GEMBA, the first MT quality assessment metric based on Large Language Models (LLMs), employs one-step prompting to achieve state-of-the-art (SOTA) in system-level MT quality estimation; however, it lacks segment-level analysis. In contrast, Chain-of-Thought (CoT) prompting outperforms one-step prompting by offering improved reasoning and explainability. In this paper, we introduce Knowledge-Prompted Estimator (KPE), a CoT prompting method that combines three one-step prompting techniques, including perplexity, token-level similarity, and sentence-level similarity. This method attains enhanced performance for segment-level estimation compared with previous deep learning models and one-step prompting approaches. Furthermore, supplementary experiments on word-level visualized alignment demonstrate that our KPE method significantly improves token alignment compared with earlier models and provides better interpretability for MT quality estimation. Code will be released upon publication.

The rise of machine learning (ML) is accompanied by several high-profile cases that have stressed the need for fairness, accountability, explainability and trust in ML systems. The existing literature has largely focused on fully automated ML approaches that try to optimize for some performance metric. However, human-centric measures like fairness, trust, explainability, etc. are subjective in nature, context-dependent, and might not correlate with conventional performance metrics. To deal with these challenges, we explore a human-centered AI approach that empowers people by providing more transparency and human control. In this dissertation, we present 5 research projects that aim to enhance explainability and fairness in classification systems and word embeddings. The first project explores the utility/downsides of introducing local model explanations as interfaces for machine teachers (crowd workers). Our study found that adding explanations supports trust calibration for the resulting ML model and enables rich forms of teaching feedback. The second project presents D-BIAS, a causality-based human-in-the-loop visual tool for identifying and mitigating social biases in tabular datasets. Apart from fairness, we found that our tool also enhances trust and accountability. The third project presents WordBias, a visual interactive tool that helps audit pre-trained static word embeddings for biases against groups, such as females, or subgroups, such as Black Muslim females. The fourth project presents DramatVis Personae, a visual analytics tool that helps identify social biases in creative writing. Finally, the last project presents an empirical study aimed at understanding the cumulative impact of multiple fairness-enhancing interventions at different stages of the ML pipeline on fairness, utility and different population groups. We conclude by discussing some of the future directions.

Large language models such as BERT and the GPT series started a paradigm shift that calls for building general-purpose models via pre-training on large datasets, followed by fine-tuning on task-specific datasets. There is now a plethora of large pre-trained models for Natural Language Processing and Computer Vision. Recently, we have seen rapid developments in the joint Vision-Language space as well, where pre-trained models such as CLIP (Radford et al., 2021) have demonstrated improvements in downstream tasks like image captioning and visual question answering. However, surprisingly there is comparatively little work on exploring these models for the task of multimodal machine translation, where the goal is to leverage image/video modality in text-to-text translation. To fill this gap, this paper surveys the landscape of language-and-vision pre-training from the lens of multimodal machine translation. We summarize the common architectures, pre-training objectives, and datasets from literature and conjecture what further is needed to make progress on multimodal machine translation.

We study cross-modal recommendation of music tracks to be used as soundtracks for videos. This problem is known as the music supervision task. We build on a self-supervised system that learns a content association between music and video. In addition to the adequacy of content, adequacy of structure is crucial in music supervision to obtain relevant recommendations. We propose a novel approach to significantly improve the system's performance using structure-aware recommendation. The core idea is to consider not only the full audio-video clips, but rather shorter segments for training and inference. We find that using semantic segments and ranking the tracks according to sequence alignment costs significantly improves the results. We investigate the impact of different ranking metrics and segmentation methods.

Training algorithms, broadly construed, are an essential part of every deep learning pipeline. Training algorithm improvements that speed up training across a wide variety of workloads (e.g., better update rules, tuning protocols, learning rate schedules, or data selection schemes) could save time, save computational resources, and lead to better, more accurate, models. Unfortunately, as a community, we are currently unable to reliably identify training algorithm improvements, or even determine the state-of-the-art training algorithm. In this work, using concrete experiments, we argue that real progress in speeding up training requires new benchmarks that resolve three basic challenges faced by empirical comparisons of training algorithms: (1) how to decide when training is complete and precisely measure training time, (2) how to handle the sensitivity of measurements to exact workload details, and (3) how to fairly compare algorithms that require hyperparameter tuning. In order to address these challenges, we introduce a new, competitive, time-to-result benchmark using multiple workloads running on fixed hardware, the AlgoPerf: Training Algorithms benchmark. Our benchmark includes a set of workload variants that make it possible to detect benchmark submissions that are more robust to workload changes than current widely-used methods. Finally, we evaluate baseline submissions constructed using various optimizers that represent current practice, as well as other optimizers that have recently received attention in the literature. These baseline results collectively demonstrate the feasibility of our benchmark, show that non-trivial gaps between methods exist, and set a provisional state-of-the-art for future benchmark submissions to try and surpass.

As the smartphone market leader, Android has been a prominent target for malware attacks. The number of malicious applications (apps) identified for it has increased continually over the past decade, creating an immense challenge for all parties involved. For market holders and researchers, in particular, the large number of samples has made manual malware detection unfeasible, leading to an influx of research that investigate Machine Learning (ML) approaches to automate this process. However, while some of the proposed approaches achieve high performance, rapidly evolving Android malware has made them unable to maintain their accuracy over time. This has created a need in the community to conduct further research, and build more flexible ML pipelines. Doing so, however, is currently hindered by a lack of systematic overview of the existing literature, to learn from and improve upon the existing solutions. Existing survey papers often focus only on parts of the ML process (e.g., data collection or model deployment), while omitting other important stages, such as model evaluation and explanation. In this paper, we address this problem with a review of 42 highly-cited papers, spanning a decade of research (from 2011 to 2021). We introduce a novel procedural taxonomy of the published literature, covering how they have used ML algorithms, what features they have engineered, which dimensionality reduction techniques they have employed, what datasets they have employed for training, and what their evaluation and explanation strategies are. Drawing from this taxonomy, we also identify gaps in knowledge and provide ideas for improvement and future work.