Pseudo-labeling is a popular semi-supervised learning technique to leverage unlabeled data when labeled samples are scarce. The generation and selection of pseudo-labels heavily rely on labeled data. Existing approaches implicitly assume that the labeled data is gold standard and 'perfect'. However, this can be violated in reality with issues such as mislabeling or ambiguity. We address this overlooked aspect and show the importance of investigating labeled data quality to improve any pseudo-labeling method. Specifically, we introduce a novel data characterization and selection framework called DIPS to extend pseudo-labeling. We select useful labeled and pseudo-labeled samples via analysis of learning dynamics. We demonstrate the applicability and impact of DIPS for various pseudo-labeling methods across an extensive range of real-world tabular and image datasets. Additionally, DIPS improves data efficiency and reduces the performance distinctions between different pseudo-labelers. Overall, we highlight the significant benefits of a data-centric rethinking of pseudo-labeling in real-world settings.

Downscaling techniques are one of the most prominent applications of Deep Learning (DL) in Earth System Modeling. A robust DL downscaling model can generate high-resolution fields from coarse-scale numerical model simulations, saving the timely and resourceful applications of regional/local models. Additionally, generative DL models have the potential to provide uncertainty information, by generating ensemble-like scenario pools, a task that is computationally prohibitive for traditional numerical simulations. In this study, we apply a Latent Diffusion Model (LDM) to downscale ERA5 data over Italy up to a resolution of 2 km. The high-resolution target data consists of results from a high-resolution dynamical downscaling performed with COSMO-CLM. Our goal is to demonstrate that recent advancements in generative modeling enable DL-based models to deliver results comparable to those of numerical dynamical downscaling models, given the same input data (i.e., ERA5 data), preserving the realism of fine-scale features and flow characteristics. The training and testing database consists of hourly data from 2000 to 2020. The target variables of this study are 2-m temperature and 10-m horizontal wind components. A selection of predictors from ERA5 is used as input to the LDM, and a residual approach against a reference UNET is leveraged in applying the LDM. The performance of the generative LDM is compared with reference baselines of increasing complexity: quadratic interpolation of ERA5, a UNET, and a Generative Adversarial Network (GAN) built on the same reference UNET. Results highlight the improvements introduced by the LDM architecture and the residual approach over these baselines. The models are evaluated on a yearly test dataset, assessing the models' performance through deterministic metrics, spatial distribution of errors, and reconstruction of frequency and power spectra distributions.

Recently, there has been increasing interest in multimodal applications that integrate text with other modalities, such as images, audio and video, to facilitate natural language interactions with multimodal AI systems. While applications involving standard modalities have been extensively explored, there is still a lack of investigation into specific data modalities such as remote sensing (RS) data. Despite the numerous potential applications of RS data, including environmental protection, disaster monitoring and land planning, available solutions are predominantly focused on specific tasks like classification, captioning and retrieval. These solutions often overlook the unique characteristics of RS data, such as its capability to systematically provide information on the same geographical areas over time. This ability enables continuous monitoring of changes in the underlying landscape. To address this gap, we propose a novel foundation model for bi-temporal RS image pairs, in the context of change detection analysis, leveraging Contrastive Learning and the LEVIR-CC dataset for both captioning and text-image retrieval. By jointly training a contrastive encoder and captioning decoder, our model add text-image retrieval capabilities, in the context of bi-temporal change detection, while maintaining captioning performances that are comparable to the state of the art. We release the source code and pretrained weights at: https://github.com/rogerferrod/RSICRC.

We introduce a new method to jointly reduce the dimension of the input and output space of a high-dimensional function. Choosing a reduced input subspace influences which output subspace is relevant and vice versa. Conventional methods focus on reducing either the input or output space, even though both are often reduced simultaneously in practice. Our coupled approach naturally supports goal-oriented dimension reduction, where either an input or output quantity of interest is prescribed. We consider, in particular, goal-oriented sensor placement and goal-oriented sensitivity analysis, which can be viewed as dimension reduction where the most important output or, respectively, input components are chosen. Both applications present difficult combinatorial optimization problems with expensive objectives such as the expected information gain and Sobol indices. By optimizing gradient-based bounds, we can determine the most informative sensors and most sensitive parameters as the largest diagonal entries of some diagnostic matrices, thus bypassing the combinatorial optimization and objective evaluation.

Few-shot named entity recognition (NER) systems recognize entities using a few labeled training examples. The general pipeline consists of a span detector to identify entity spans in text and an entity-type classifier to assign types to entities. Current span detectors rely on extensive manual labeling to guide training. Almost every span detector requires initial training on basic span features followed by adaptation to task-specific features. This process leads to repetitive training of the basic span features among span detectors. Additionally, metric-based entity-type classifiers, such as prototypical networks, typically employ a specific metric that gauges the distance between the query sample and entity-type referents, ultimately assigning the most probable entity type to the query sample. However, these classifiers encounter the sample dependency problem, primarily stemming from the limited samples available for each entity-type referent. To address these challenges, we proposed an improved few-shot NER pipeline. First, we introduce a steppingstone span detector that is pre-trained on open-domain Wikipedia data. It can be used to initialize the pipeline span detector to reduce the repetitive training of basic features. Second, we leverage a large language model (LLM) to set reliable entity-type referents, eliminating reliance on few-shot samples of each type. Our model exhibits superior performance with fewer training steps and human-labeled data compared with baselines, as demonstrated through extensive experiments on various datasets. Particularly in fine-grained few-shot NER settings, our model outperforms strong baselines, including ChatGPT. We will publicly release the code, datasets, LLM outputs, and model checkpoints.

Buildings play a crucial role in human well-being, influencing occupant comfort, health, and safety. Additionally, they contribute significantly to global energy consumption, accounting for one-third of total energy usage, and carbon emissions. Optimizing building performance presents a vital opportunity to combat climate change and promote human flourishing. However, research in building analytics has been hampered by the lack of accessible, available, and comprehensive real-world datasets on multiple building operations. In this paper, we introduce the Building TimeSeries (BTS) dataset. Our dataset covers three buildings over a three-year period, comprising more than ten thousand timeseries data points with hundreds of unique ontologies. Moreover, the metadata is standardized using the Brick schema. To demonstrate the utility of this dataset, we performed benchmarks on two tasks: timeseries ontology classification and zero-shot forecasting. These tasks represent an essential initial step in addressing challenges related to interoperability in building analytics.

We consider a ubiquitous scenario in the study of Influence Maximization (IM), in which there is limited knowledge about the topology of the diffusion network. We set the IM problem in a multi-round diffusion campaign, aiming to maximize the number of distinct users that are influenced. Leveraging the capability of bandit algorithms to effectively balance the objectives of exploration and exploitation, as well as the expressivity of neural networks, our study explores the application of neural bandit algorithms to the IM problem. We propose the framework IM-GNB (Influence Maximization with Graph Neural Bandits), where we provide an estimate of the users' probabilities of being influenced by influencers (also known as diffusion seeds). This initial estimate forms the basis for constructing both an exploitation graph and an exploration one. Subsequently, IM-GNB handles the exploration-exploitation tradeoff, by selecting seed nodes in real-time using Graph Convolutional Networks (GCN), in which the pre-estimated graphs are employed to refine the influencers' estimated rewards in each contextual setting. Through extensive experiments on two large real-world datasets, we demonstrate the effectiveness of IM-GNB compared with other baseline methods, significantly improving the spread outcome of such diffusion campaigns, when the underlying network is unknown.

The aim of this project was to develop a new Reservoir Computer implementation, based on a chaotic Chua circuit. In addition to suitable classification and regression benchmarks, the Reservoir Computer was applied to Post-Quantum Cryptography, with its suitability for this application investigated and assessed. The cryptographic algorithm utilised was the Learning with Errors problem, for both encryption and decryption. To achieve this, the Chua circuit was characterised, in simulation, and by physical circuit testing. The Reservoir Computer was designed and implemented using the results of the characterisation. As part of this development, noise was considered and mitigated. The benchmarks demonstrate that the Reservoir Computer can achieve current literature benchmarks with low error. However, the results with Learning with Errors suggest that a Chua-based Reservoir Computer is not sufficiently complex to tackle the high non-linearity in Post-Quantum Cryptography. Future work would involve researching the use of different combinations of multiple Chua Reservoir Computers in larger neural network architectures. Such architectures may produce the required high-dimensional behaviour to achieve the Learning with Errors problem. This project is believed to be only the second instance of a Chua-based Reservoir Computer in academia, and it is the first to be applied to challenging real-world tasks such as Post-Quantum Cryptography. It is also original by its investigation of hitherto unexplored parameters, and their impact on performance. It demonstrates a proof-of-concept for a mass-producible, inexpensive, low-power consumption hardware neural network. It also enables the next stages in research to occur, paving the road for using Chua-based Reservoir Computers across various applications.

Internal solitary waves (ISWs) are gravity waves that are often observed in the interior ocean rather than the surface. They hold significant importance due to their capacity to carry substantial energy, thus influence pollutant transport, oil platform operations, submarine navigation, etc. Researchers have studied ISWs through optical images, synthetic aperture radar (SAR) images, and altimeter data from remote sensing instruments. However, cloud cover in optical remote sensing images variably obscures ground information, leading to blurred or missing surface observations. As such, this paper aims at altimeter-based machine learning solutions to automatically locate ISWs. The challenges, however, lie in the following two aspects: 1) the altimeter data has low resolution, which requires a strong machine learner; 2) labeling data is extremely labor-intensive, leading to very limited data for training. In recent years, the grand progress of deep learning demonstrates strong learning capacity given abundant data. Besides, more recent studies on efficient learning and self-supervised learning laid solid foundations to tackle the aforementioned challenges. In this paper, we propose to inject prior knowledge to achieve a strong and efficient learner. Specifically, intrinsic patterns in altimetry data are efficiently captured using a scale-translation equivariant convolutional neural network (ST-ECNN). By considering inherent symmetries in neural network design, ST-ECNN achieves higher efficiency and better performance than baseline models. Furthermore, we also introduce prior knowledge from massive unsupervised data to enhance our solution using the SimCLR framework for pre-training. Our final solution achieves an overall better performance than baselines on our handcrafted altimetry dataset. Data and codes are available at https://github.com/ZhangWan-byte/Internal_Solitary_Wave_Localization .

Large language models (LLMs) have significantly advanced various natural language processing tasks, but deploying them remains computationally expensive. Knowledge distillation (KD) is a promising solution, enabling the transfer of capabilities from larger teacher LLMs to more compact student models. Particularly, sequence-level KD, which distills rationale-based reasoning processes instead of merely final outcomes, shows great potential in enhancing students' reasoning capabilities. However, current methods struggle with sequence level KD under long-tailed data distributions, adversely affecting generalization on sparsely represented domains. We introduce the Multi-Stage Balanced Distillation (BalDistill) framework, which iteratively balances training data within a fixed computational budget. By dynamically selecting representative head domain examples and synthesizing tail domain examples, BalDistill achieves state-of-the-art performance across diverse long-tailed datasets, enhancing both the efficiency and efficacy of the distilled models.