This paper provides a first milestone in measuring the floorspace of buildings (that is, building footprint and height) for 40 major Chinese cities. The intent is to maximize city coverage and, eventually provide longitudinal data. Doing so requires building on imagery that is of a medium-fine-grained granularity, as larger cross sections of cities and longer time series for them are only available in such format. We use a multi-task object segmenter approach to learn the building footprint and height in the same framework in parallel: (1) we determine the surface area is covered by any buildings (the square footage of occupied land); (2) we determine floorspace from multi-image representations of buildings from various angles to determine the height of buildings. We use Sentinel-1 and -2 satellite images as our main data source. The benefits of these data are their large cross-sectional and longitudinal scope plus their unrestricted accessibility. We provide a detailed description of our data, algorithms, and evaluations. In addition, we analyze the quality of reference data and their role for measuring the building floorspace with minimal error. We conduct extensive quantitative and qualitative analyses with Shenzhen as a case study using our multi-task learner. Finally, we conduct correlation studies between our results (on both pixel and aggregated urban area levels) and nightlight data to gauge the merits of our approach in studying urban development. Our data and codebase are publicly accessible under https://gitlab.ethz.ch/raox/urban-satellite-public-v2.

This paper presents a rich knowledge representation language aimed at formalizing causal knowledge. This language is used for accurately and directly formalizing common benchmark examples from the literature of actual causality. A definition of cause is presented and used to analyze the actual causes of changes with respect to sequences of actions representing those examples.

Online tuning of real-world plants is a complex optimisation problem that continues to require manual intervention by experienced human operators. Autonomous tuning is a rapidly expanding field of research, where learning-based methods, such as Reinforcement Learning-trained Optimisation (RLO) and Bayesian optimisation (BO), hold great promise for achieving outstanding plant performance and reducing tuning times. Which algorithm to choose in different scenarios, however, remains an open question. Here we present a comparative study using a routine task in a real particle accelerator as an example, showing that RLO generally outperforms BO, but is not always the best choice. Based on the study's results, we provide a clear set of criteria to guide the choice of algorithm for a given tuning task. These can ease the adoption of learning-based autonomous tuning solutions to the operation of complex real-world plants, ultimately improving the availability and pushing the limits of operability of these facilities, thereby enabling scientific and engineering advancements.

Quantum theory, originally proposed as a physical theory to describe the motions of microscopic particles, has been applied to various non-physics domains involving human cognition and decision-making that are inherently uncertain and exhibit certain non-classical, quantum-like characteristics. Sentiment analysis is a typical example of such domains. In the last few years, by leveraging the modeling power of quantum probability (a non-classical probability stemming from quantum mechanics methodology) and deep neural networks, a range of novel quantum-cognitively inspired models for sentiment analysis have emerged and performed well. This survey presents a timely overview of the latest developments in this fascinating cross-disciplinary area. We first provide a background of quantum probability and quantum cognition at a theoretical level, analyzing their advantages over classical theories in modeling the cognitive aspects of sentiment analysis. Then, recent quantum-cognitively inspired models are introduced and discussed in detail, focusing on how they approach the key challenges of the sentiment analysis task. Finally, we discuss the limitations of the current research and highlight future research directions.

Knowledge graphs (KGs) are an important tool for representing complex relationships between entities in the biomedical domain. Several methods have been proposed for learning embeddings that can be used to predict new links in such graphs. Some methods ignore valuable attribute data associated with entities in biomedical KGs, such as protein sequences, or molecular graphs. Other works incorporate such data, but assume that entities can be represented with the same data modality. This is not always the case for biomedical KGs, where entities exhibit heterogeneous modalities that are central to their representation in the subject domain. We propose a modular framework for learning embeddings in KGs with entity attributes, that allows encoding attribute data of different modalities while also supporting entities with missing attributes. We additionally propose an efficient pretraining strategy for reducing the required training runtime. We train models using a biomedical KG containing approximately 2 million triples, and evaluate the performance of the resulting entity embeddings on the tasks of link prediction, and drug-protein interaction prediction, comparing against methods that do not take attribute data into account. In the standard link prediction evaluation, the proposed method results in competitive, yet lower performance than baselines that do not use attribute data. When evaluated in the task of drug-protein interaction prediction, the method compares favorably with the baselines. We find settings involving low degree entities, which make up for a substantial amount of the set of entities in the KG, where our method outperforms the baselines. Our proposed pretraining strategy yields significantly higher performance while reducing the required training runtime. Our implementation is available at https://github.com/elsevier-AI-Lab/BioBLP .

Recently, compressive text summarisation offers a balance between the conciseness issue of extractive summarisation and the factual hallucination issue of abstractive summarisation. However, most existing compressive summarisation methods are supervised, relying on the expensive effort of creating a new training dataset with corresponding compressive summaries. In this paper, we propose an efficient and interpretable compressive summarisation method that utilises unsupervised dual-agent reinforcement learning to optimise a summary's semantic coverage and fluency by simulating human judgment on summarisation quality. Our model consists of an extractor agent and a compressor agent, and both agents have a multi-head attentional pointer-based structure. The extractor agent first chooses salient sentences from a document, and then the compressor agent compresses these extracted sentences by selecting salient words to form a summary without using reference summaries to compute the summary reward. To our best knowledge, this is the first work on unsupervised compressive summarisation. Experimental results on three widely used datasets (e.g., Newsroom, CNN/DM, and XSum) show that our model achieves promising performance and a significant improvement on Newsroom in terms of the ROUGE metric, as well as interpretability of semantic coverage of summarisation results.

Large, high-quality datasets are crucial for training Large Language Models (LLMs). However, so far, there are few datasets available for specialized critical domains such as law and the available ones are often only for the English language. We curate and release MultiLegalPile, a 689GB corpus in 24 languages from 17 jurisdictions. The MultiLegalPile corpus, which includes diverse legal data sources with varying licenses, allows for pretraining NLP models under fair use, with more permissive licenses for the Eurlex Resources and Legal mC4 subsets. We pretrain two RoBERTa models and one Longformer multilingually, and 24 monolingual models on each of the language-specific subsets and evaluate them on LEXTREME. Additionally, we evaluate the English and multilingual models on LexGLUE. Our multilingual models set a new SotA on LEXTREME and our English models on LexGLUE. We release the dataset, the trained models, and all of the code under the most open possible licenses.

SEARCH SUSPENDED - No survivors found after plane violates DC airspace, scrambles military before crashing in Virginia. LAND OF THE FREE? - Capitol Police spark outrage as youth choir's national anthem performance halted. 'BEST SOLUTION' - AI could help solve NJ missing child mystery, become model for cold case probes. RECORD SCRATCH - 'American Pie' icon Don McLean weighs in on AI's effect on the music industry. WHAT'S IN STORE - Target backs organization pushing US demilitarization, Mt. 'IT HAS TO BE JOE BIDEN' - Ex-FBI director James Comey speaks out on 2024 race.

Federated learning is an emerging machine learning paradigm that enables clients to train collaboratively without exchanging local data. The clients participating in the training process have a crucial impact on the convergence rate, learning efficiency, and model generalization. In this work, we propose FilFL, a new approach to optimizing client participation and training by introducing client filtering. FilFL periodically filters the available clients to identify a subset that maximizes a combinatorial objective function using an efficient greedy filtering algorithm. From this filtered-in subset, clients are then selected for the training process. We provide a thorough analysis of FilFL convergence in a heterogeneous setting and evaluate its performance across diverse vision and language tasks and realistic federated scenarios with time-varying client availability. Our empirical results demonstrate several benefits of our approach, including improved learning efficiency, faster convergence, and up to 10 percentage points higher test accuracy compared to scenarios where client filtering is not utilized.

We recover the Riemannian gradient of a given function defined on interior points of a Riemannian submanifold in the Euclidean space based on a sample of function evaluations at points in the submanifold. This approach is based on the estimates of the Laplace-Beltrami operator proposed in the diffusion-maps theory. The Riemannian gradient estimates do not involve differential terms. Analytical convergence results of the Riemannian gradient expansion are proved. We apply the Riemannian gradient estimate in a gradient-based algorithm providing a derivative-free optimization method. We test and validate several applications, including tomographic reconstruction from an unknown random angle distribution, and the sphere packing problem in dimensions 2 and 3.