In machine learning systems, bias mitigation approaches aim to make outcomes fairer across privileged and unprivileged groups. Bias mitigation methods work in different ways and have known "waterfall" effects, e.g., mitigating bias at one place may manifest bias elsewhere. In this paper, we aim to characterise impacted cohorts when mitigation interventions are applied. To do so, we treat intervention effects as a classification task and learn an explainable meta-classifier to identify cohorts that have altered outcomes. We examine a range of bias mitigation strategies that work at various stages of the model life cycle. We empirically demonstrate that our meta-classifier is able to uncover impacted cohorts. Further, we show that all tested mitigation strategies negatively impact a non-trivial fraction of cases, i.e., people who receive unfavourable outcomes solely on account of mitigation efforts. This is despite improvement in fairness metrics. We use these results as a basis to argue for more careful audits of static mitigation interventions that go beyond aggregate metrics.

We consider a setting where a population of artificial learners is given, and the objective is to optimize aggregate measures of performance, under constraints on training resources. The problem is motivated by the study of peer learning in human educational systems. In this context, we study natural knowledge diffusion processes in networks of interacting artificial learners. By `natural', we mean processes that reflect human peer learning where the students' internal state and learning process is mostly opaque, and the main degree of freedom lies in the formation of peer learning groups by a coordinator who can potentially evaluate the learners before assigning them to peer groups. Among else, we empirically show that such processes indeed make effective use of the training resources, and enable the design of modular neural models that have the capacity to generalize without being prone to overfitting noisy labels.

Programming language understanding and representation (a.k.a code representation learning) has always been a hot and challenging task in software engineering. It aims to apply deep learning techniques to produce numerical representations of the source code features while preserving its semantics. These representations can be used for facilitating subsequent code-related tasks. The abstract syntax tree (AST), a fundamental code feature, illustrates the syntactic information of the source code and has been widely used in code representation learning. However, there is still a lack of systematic and quantitative evaluation of how well AST-based code representation facilitates subsequent code-related tasks. In this paper, we first conduct a comprehensive empirical study to explore the effectiveness of the AST-based code representation in facilitating follow-up code-related tasks. To do so, we compare the performance of models trained with code token sequence (Token for short) based code representation and AST-based code representation on three popular types of code-related tasks. Surprisingly, the overall quantitative statistical results demonstrate that models trained with AST-based code representation consistently perform worse across all three tasks compared to models trained with Token-based code representation. Our further quantitative analysis reveals that models trained with AST-based code representation outperform models trained with Token-based code representation in certain subsets of samples across all three tasks. We also conduct comprehensive experiments to evaluate and reveal the impact of the choice of AST parsing/preprocessing/encoding methods on AST-based code representation and subsequent code-related tasks. Our study provides future researchers with detailed guidance on how to select solutions at each stage to fully exploit AST.

Active learning aims to enhance model performance by strategically labeling informative data points. While extensively studied, its effectiveness on large-scale, real-world datasets remains underexplored. Existing research primarily focuses on single-source data, ignoring the multi-domain nature of real-world data. We introduce a multi-domain active learning benchmark to bridge this gap. Our benchmark demonstrates that traditional single-domain active learning strategies are often less effective than random selection in multi-domain scenarios. We also introduce CLIP-GeoYFCC, a novel large-scale image dataset built around geographical domains, in contrast to existing genre-based domain datasets. Analysis on our benchmark shows that all multi-domain strategies exhibit significant tradeoffs, with no strategy outperforming across all datasets or all metrics, emphasizing the need for future research.

Supervised deep learning methods have shown promise in undersampled Magnetic Resonance Imaging (MRI) reconstruction, but their requirement for paired data limits their generalizability to the diverse MRI acquisition parameters. Recently, unsupervised controllable generative diffusion models have been applied to undersampled MRI reconstruction, without paired data or model retraining for different MRI acquisitions. However, diffusion models are generally slow in sampling and state-of-the-art acceleration techniques can lead to sub-optimal results when directly applied to the controllable generation process. This study introduces a new algorithm called Predictor-Projector-Noisor (PPN), which enhances and accelerates controllable generation of diffusion models for undersampled MRI reconstruction. Our results demonstrate that PPN produces high-fidelity MR images that conform to undersampled k-space measurements with significantly shorter reconstruction time than other controllable sampling methods. In addition, the unsupervised PPN accelerated diffusion models are adaptable to different MRI acquisition parameters, making them more practical for clinical use than supervised learning techniques.

Deep learning has successfully solved a wide range of tasks in 2D vision as a dominant AI technique. Recently, deep learning on 3D point clouds is becoming increasingly popular for addressing various tasks in this field. Despite remarkable achievements, deep learning algorithms are vulnerable to adversarial attacks. These attacks are imperceptible to the human eye but can easily fool deep neural networks in the testing and deployment stage. To encourage future research, this survey summarizes the current progress on adversarial attack and defense techniques on point cloud classification.This paper first introduces the principles and characteristics of adversarial attacks and summarizes and analyzes adversarial example generation methods in recent years. Additionally, it provides an overview of defense strategies, organized into data-focused and model-focused methods. Finally, it presents several current challenges and potential future research directions in this domain.

An efficient method for next-best-view (NBV) estimation with high accuracy in the case of the limited camera field of view (FOV) was proposed. Abstract: Fusion of three-dimensional (3D) and multispectral (MS) imaging data has a great potential for high-throughput plant phenotyping of structural and biochemical as well as physiological traits simultaneously, which is important for decision support in agriculture and for crop breeders in selecting the best genotypes. However, lacking of 3D data integrity of various plant canopy structures and low-quality of MS images caused by the complex illumination effects make a great challenge, especially at the proximal imaging scale. Therefore, this study proposed a novel approach for adaptive data acquisition and radiometric calibration to generate high-quality 3D multispectral point clouds (3DMPCs) of plants. An efficient next-best-view (NBV) planning method based on an unmanned ground vehicle (UGV) plant phenotyping system with a multisensor-equipped robotic arm was proposed to achieve adaptive data acquisition. The neural reference field (NeREF) was employed to predict the digital number (DN) values of the hemispherical reference for radiometric calibration. For NBV planning, the average total time for single plant at a joint speed of 1.55 rad/s was about 62.8 s, with an average reduction of 18.0% compared to the unplanned. The integrity of the wholeplant data was improved by an average of 23.6% compared to the fixed viewpoints alone. Compared with the ASD measurements, the average root mean square error (RMSE) of the reflectance spectra obtained from 3DMPCs at different regions of interest was 0.08 with an average decrease of 58.93% compared to the results obtained from the single-frame of MS images without 3D radiometric calibration. The 3Dcalibrated plant 3DMPCs improved the predictive accuracy of partial least squares regression (PLSR) for chlorophyll content, with an average increase of 0.07 in the coefficient of determination (R Our approach introduced a fresh perspective on generating high-quality 3DMPCs of plants under the natural light condition, enabling more precise analysis of plant morphological and physiological parameters. Keywords: adaptive data acquisition; 3DMPC; NBV planning; radiometric calibration; NeREF; chlorophyll content 1. Introduction High-throughput plant phenotyping provides an unprecedented way to systematically evaluate plant development and functionality with the precise quantification of morphological, physiological, biochemical, and performance traits over the whole growth period. It can help on decision support in agriculture, for ecological diversity studies, and for crop breeding in the selection of superior genotypes to improve crop performance, and thus revolutionize the agriculture and breeding strategies to meet the future need of agricultural sustainable development (Freschet et al. 2018; Hu and Schmidhalter 2023).

GPT-2 [40], GPT-3 [4] and GPT-Neo [3] have been shown to generate high-quality texts for these tasks. To generate a sequence of A key component of generating text from modern language models tokens, LMs produce a probability distribution over the vocabulary (LM) is the selection and tuning of decoding algorithms. These algorithms at each time step, from which the predicted token is drawn. Enumerating determine how to generate text from the internal probability all possible output sequences for a given input and choosing distribution generated by the LM. The process of choosing a decoding the one with the highest probability is intractable; furthermore, algorithm and tuning its hyperparameters takes significant relatively low-probability sequences may even be desirable for certain time, manual effort, and computation, and it also requires extensive tasks (e.g., creative writing). Therefore, LMs rely on decoding human evaluation. Therefore, the identity and hyperparameters of algorithms to decide which output tokens to produce based on their such decoding algorithms are considered to be extremely valuable probabilities, i.e., to decode the text.

Myocarditis is a significant cardiovascular disease (CVD) that poses a threat to the health of many individuals by causing damage to the myocardium. The occurrence of microbes and viruses, including the likes of HIV, plays a crucial role in the development of myocarditis disease (MCD). The images produced during cardiac magnetic resonance imaging (CMRI) scans are low contrast, which can make it challenging to diagnose cardiovascular diseases. In other hand, checking numerous CMRI slices for each CVD patient can be a challenging task for medical doctors. To overcome the existing challenges, researchers have suggested the use of artificial intelligence (AI)-based computer-aided diagnosis systems (CADS). The presented paper outlines a CADS for the detection of MCD from CMR images, utilizing deep learning (DL) methods. The proposed CADS consists of several steps, including dataset, preprocessing, feature extraction, classification, and post-processing. First, the Z-Alizadeh dataset was selected for the experiments. Subsequently, the CMR images underwent various preprocessing steps, including denoising, resizing, as well as data augmentation (DA) via CutMix and MixUp techniques. In the following, the most current deep pre-trained and transformer models are used for feature extraction and classification on the CMR images. The findings of our study reveal that transformer models exhibit superior performance in detecting MCD as opposed to pre-trained architectures. In terms of DL architectures, the Turbulence Neural Transformer (TNT) model exhibited impressive accuracy, reaching 99.73% utilizing a 10-fold cross-validation approach. Additionally, to pinpoint areas of suspicion for MCD in CMRI images, the Explainable-based Grad Cam method was employed.

Contrastive learning is a highly successful technique for learning representations of data from labeled tuples, specifying the distance relations within the tuple. We study the sample complexity of contrastive learning, i.e. the minimum number of labeled tuples sufficient for getting high generalization accuracy. We give tight bounds on the sample complexity in a variety of settings, focusing on arbitrary distance functions, both general $\ell_p$-distances, and tree metrics. Our main result is an (almost) optimal bound on the sample complexity of learning $\ell_p$-distances for integer $p$. For any $p \ge 1$ we show that $\tilde \Theta(\min(nd,n^2))$ labeled tuples are necessary and sufficient for learning $d$-dimensional representations of $n$-point datasets. Our results hold for an arbitrary distribution of the input samples and are based on giving the corresponding bounds on the Vapnik-Chervonenkis/Natarajan dimension of the associated problems. We further show that the theoretical bounds on sample complexity obtained via VC/Natarajan dimension can have strong predictive power for experimental results, in contrast with the folklore belief about a substantial gap between the statistical learning theory and the practice of deep learning.