Federated Learning (FL) offers a compelling method for training machine learning models with a focus on preserving data privacy. The presence of system heterogeneity and statistical heterogeneity, recognized challenges in FL, arises from the diversity of client hardware, network, and dataset distribution. This diversity can critically affect the training pace and the performance of models. While many studies address either system or statistical heterogeneity by introducing communication-efficient or stable convergence algorithms, addressing these challenges in isolation often leads to compromises due to unaddressed heterogeneity. In response, this paper introduces FedShift, a novel algorithm designed to enhance both the training speed and the models' accuracy in a dual heterogeneity scenario. Our solution can improve client engagement through quantization and mitigate the adverse effects on performance typically associated with quantization by employing a shifting technique. This technique has proven to enhance accuracy by an average of 3.9% in diverse heterogeneity environments.

Given a data matrix, where rows represent observations and columns represent variables or features, co-clustering, also known as bi-clustering aims to infer a row partition and a column partition simultaneously. The resulting partition is composed of homogeneous blocks. When a dataset exhibits a dual structure between observations and variables, co-clustering outperforms conventional clustering algorithms which only infers a row partition without considering the relationships between observations and variables. Co-clustering is a powerful data mining tool for two-dimensional data and is widely applied in various fields such as bioinformatics [1]. To tackle the co-clustering problem, the Latent Block Model (LBM) was introduced by [2].

Despite the predominance of contextualized embeddings in NLP, approaches to detect semantic change relying on these embeddings and clustering methods underperform simpler counterparts based on static word embeddings. This stems from the poor quality of the clustering methods to produce sense clusters -- which struggle to capture word senses, especially those with low frequency. This issue hinders the next step in examining how changes in word senses in one language influence another. To address this issue, we propose a graph-based clustering approach to capture nuanced changes in both high- and low-frequency word senses across time and languages, including the acquisition and loss of these senses over time. Our experimental results show that our approach substantially surpasses previous approaches in the SemEval2020 binary classification task across four languages. Moreover, we showcase the ability of our approach as a versatile visualization tool to detect semantic changes in both intra-language and inter-language setups. We make our code and data publicly available.

Internet-based economies and societies are drowning in deceptive attacks. These attacks take many forms, such as fake news, phishing, and job scams, which we call ``domains of deception.'' Machine-learning and natural-language-processing researchers have been attempting to ameliorate this precarious situation by designing domain-specific detectors. Only a few recent works have considered domain-independent deception. We collect these disparate threads of research and investigate domain-independent deception. First, we provide a new computational definition of deception and break down deception into a new taxonomy. Then, we analyze the debate on linguistic cues for deception and supply guidelines for systematic reviews. Finally, we investigate common linguistic features and give evidence for knowledge transfer across different forms of deception.

Self-supervision is one of the hallmarks of representation learning in the increasingly popular suite of foundation models including large language models such as BERT and GPT-3, but it has not been pursued in the context of multivariate event streams, to the best of our knowledge. We introduce a new paradigm for self-supervised learning for multivariate point processes using a transformer encoder. Specifically, we design a novel pre-training strategy for the encoder where we not only mask random event epochs but also insert randomly sampled "void" epochs where an event does not occur; this differs from the typical discrete-time pretext tasks such as word-masking in BERT but expands the effectiveness of masking to better capture continuous-time dynamics. To improve downstream tasks, we introduce a contrasting module that compares real events to simulated void instances. The pre-trained model can subsequently be fine-tuned on a potentially much smaller event dataset, similar conceptually to the typical transfer of popular pre-trained language models. We demonstrate the effectiveness of our proposed paradigm on the next-event prediction task using synthetic datasets and 3 real applications, observing a relative performance boost of as high as up to 20% compared to state-of-the-art models.

Statistical learning theory is the foundation of machine learning, providing theoretical bounds for the risk of models learnt from a (single) training set, assumed to issue from an unknown probability distribution. In actual deployment, however, the data distribution may (and often does) vary, causing domain adaptation/generalization issues. In this paper we lay the foundations for a `credal' theory of learning, using convex sets of probabilities (credal sets) to model the variability in the data-generating distribution. Such credal sets, we argue, may be inferred from a finite sample of training sets. Bounds are derived for the case of finite hypotheses spaces (both assuming realizability or not) as well as infinite model spaces, which directly generalize classical results.

Many machine learning models have been proposed to classify phenotypes from gene expression data. In addition to their good performance, these models can potentially provide some understanding of phenotypes by extracting explanations for their decisions. These explanations often take the form of a list of genes ranked in order of importance for the predictions, the highest-ranked genes being interpreted as linked to the phenotype. We discuss the biological and the methodological limitations of such explanations. Experiments are performed on several datasets gathering cancer and healthy tissue samples from the TCGA, GTEx and TARGET databases. A collection of machine learning models including logistic regression, multilayer perceptron, and graph neural network are trained to classify samples according to their cancer type. Gene rankings are obtained from explainability methods adapted to these models, and compared to the ones from classical statistical feature selection methods such as mutual information, DESeq2, and EdgeR. Interestingly, on simple tasks, we observe that the information learned by black-box neural networks is related to the notion of differential expression. In all cases, a small set containing the best-ranked genes is sufficient to achieve a good classification. However, these genes differ significantly between the methods and similar classification performance can be achieved with numerous lower ranked genes. In conclusion, although these methods enable the identification of biomarkers characteristic of certain pathologies, our results question the completeness of the selected gene sets and thus of explainability by the identification of the underlying biological processes.

Concept Bottleneck Models (CBMs) are considered inherently interpretable because they first predict a set of human-defined concepts before using these concepts to predict the output of a downstream task. For inherent interpretability to be fully realised, and ensure trust in a model's output, we need to guarantee concepts are predicted based on semantically mapped input features. For example, one might expect the pixels representing a broken bone in an image to be used for the prediction of a fracture. However, current literature indicates this is not the case, as concept predictions are often mapped to irrelevant input features. We hypothesise that this occurs when concept annotations are inaccurate or how input features should relate to concepts is unclear. In general, the effect of dataset labelling on concept representations in CBMs remains an understudied area. Therefore, in this paper, we examine how CBMs learn concepts from datasets with fine-grained concept annotations. We demonstrate that CBMs can learn concept representations with semantic mapping to input features by removing problematic concept correlations, such as two concepts always appearing together. To support our evaluation, we introduce a new synthetic image dataset based on a playing cards domain, which we hope will serve as a benchmark for future CBM research. For validation, we provide empirical evidence on a real-world dataset of chest X-rays, to demonstrate semantically meaningful concepts can be learned in real-world applications.

Addressing biases in AI models is crucial for ensuring fair and accurate predictions. However, obtaining large, unbiased datasets for training can be challenging. This paper proposes a comprehensive approach using multiple methods to remove bias in AI models, with only a small dataset and a potentially biased pretrained model. We train multiple models with the counter-bias of the pre-trained model through data splitting, local training, and regularized fine-tuning, gaining potentially counter-biased models. Then, we employ ensemble learning for all models to reach unbiased predictions. To further accelerate the inference time of our ensemble model, we conclude our solution with knowledge distillation that results in a single unbiased neural network. We demonstrate the effectiveness of our approach through experiments on the CIFAR10 and HAM10000 datasets, showcasing promising results. This work contributes to the ongoing effort to create more unbiased and reliable AI models, even with limited data availability.

Early time classification algorithms aim to label a stream of features without processing the full input stream, while maintaining accuracy comparable to that achieved by applying the classifier to the entire input. In this paper, we introduce a statistical framework that can be applied to any sequential classifier, formulating a calibrated stopping rule. This data-driven rule attains finite-sample, distribution-free control of the accuracy gap between full and early-time classification. We start by presenting a novel method that builds on the Learn-then-Test calibration framework to control this gap marginally, on average over i.i.d. instances. As this algorithm tends to yield an excessively high accuracy gap for early halt times, our main contribution is the proposal of a framework that controls a stronger notion of error, where the accuracy gap is controlled conditionally on the accumulated halt times. Numerical experiments demonstrate the effectiveness, applicability, and usefulness of our method. We show that our proposed early stopping mechanism reduces up to 94% of timesteps used for classification while achieving rigorous accuracy gap control.