Supervised learning is a pillar of machine learning, thus this supervision requires labels, which is most of the time an expensive task. While transfer learning and generalisation can be seen as solutions, but due to domain shift, in other words, divergence between the domains (i.e. the difference between probability distributions of two domains), the task model trained on labelled data from domain A (source) and tested on unlabelled data from domain B (target) will have a decay in the performance in comparison with training and testing on the same domain B, which is out capacity in the absence of labels. To address these challenges, domain adaptation approaches are employed. Within these approaches, some can manage adaptation between a single source and a single target, referred to as single-source domain adaptation (SDA) methods, while others can handle adaptation between multiple sources and a single target, known as Multi-source domain adaptation (MDA) methods. Several works have been proposed in MDA, [Mansour et al., 2021] defended a theoretical analysis considering the assumption says that the target is a convex combination of source domains.

Domain adaptation arises as an important problem in statistical learning theory when the data-generating processes differ between training and test samples, respectively called source and target domains. Recent theoretical advances show that the success of domain adaptation algorithms heavily relies on their ability to minimize the divergence between the probability distributions of the source and target domains. However, minimizing this divergence cannot be done independently of the minimization of other key ingredients such as the source risk or the combined error of the ideal joint hypothesis. The trade-off between these terms is often ensured by algorithmic solutions that remain implicit and not directly reflected by the theoretical guarantees. To get to the bottom of this issue, we propose in this paper a new theoretical framework for domain adaptation through hierarchical optimal transport. This framework provides more explicit generalization bounds and allows us to consider the natural hierarchical organization of samples in both domains into classes or clusters. Additionally, we provide a new divergence measure between the source and target domains called Hierarchical Wasserstein distance that indicates under mild assumptions, which structures have to be aligned to lead to a successful adaptation.

Semi-supervised learning provides an effective paradigm for leveraging unlabeled data to improve a model\s performance. Among the many strategies proposed, graph-based methods have shown excellent properties, in particular since they allow to solve directly the transductive tasks according to Vapnik\s principle and they can be extended efficiently for inductive tasks. In this paper, we propose a novel approach for the transductive semi-supervised learning, using a complete bipartite edge-weighted graph. The proposed approach uses the regularized optimal transport between empirical measures defined on labelled and unlabelled data points in order to obtain an affinity matrix from the optimal transport plan. This matrix is further used to propagate labels through the vertices of the graph in an incremental process ensuring the certainty of the predictions by incorporating a certainty score based on Shannon\s entropy. We also analyze the convergence of our approach and we derive an efficient way to extend it for out-of-sample data. Experimental analysis was used to compare the proposed approach with other label propagation algorithms on 12 benchmark datasets, for which we surpass state-of-the-art results. We release our code.

All famous machine learning algorithms that comprise both supervised and semi-supervised learning work well only under a common assumption: the training and test data follow the same distribution. When the distribution changes, most statistical models must be reconstructed from newly collected data, which for some applications can be costly or impossible to obtain. Therefore, it has become necessary to develop approaches that reduce the need and the effort to obtain new labeled samples by exploiting data that are available in related areas, and using these further across similar fields. This has given rise to a new machine learning framework known as transfer learning: a learning setting inspired by the capability of a human being to extrapolate knowledge across tasks to learn more efficiently. Despite a large amount of different transfer learning scenarios, the main objective of this survey is to provide an overview of the state-of-the-art theoretical results in a specific, and arguably the most popular, sub-field of transfer learning, called domain adaptation. In this sub-field, the data distribution is assumed to change across the training and the test data, while the learning task remains the same. We provide a first up-to-date description of existing results related to domain adaptation problem that cover learning bounds based on different statistical learning frameworks.

In this paper, we present a novel method for co-clustering, an unsupervised learning approach that aims at discovering homogeneous groups of data instances and features by grouping them simultaneously. The proposed method uses the entropy regularized optimal transport between empirical measures defined on data instances and features in order to obtain an estimated joint probability density function represented by the optimal coupling matrix. This matrix is further factorized to obtain the induced row and columns partitions using multiscale representations approach. To justify our method theoretically, we show how the solution of the regularized optimal transport can be seen from the variational inference perspective thus motivating its use for co-clustering. The algorithm derived for the proposed method and its kernelized version based on the notion of Gromov-Wasserstein distance are fast, accurate and can determine automatically the number of both row and column clusters. These features are vividly demonstrated through extensive experimental evaluations.

The ability of a human being to extrapolate previously gained knowledge to other domains inspired a new family of methods in machine learning called transfer learning. Transfer learning is often based on the assumption that objects in both target and source domains share some common feature and/or data space. In this paper, we propose a simple and intuitive approach that minimizes iteratively the distance between source and target task distributions by optimizing the kernel target alignment (KTA). We show that this procedure is suitable for transfer learning by relating it to Hilbert-Schmidt Independence Criterion (HSIC) and Quadratic Mutual Information (QMI) maximization. We run our method on benchmark computer vision data sets and show that it can outperform some state-of-art methods.

Data mining allows the exploration of sequences of phenomena, whereas one usually tends to focus on isolated phenomena or on the relation between two phenomena. It offers invaluable tools for theoretical analyses and exploration of the structure of sentences, texts, dialogues, and speech. We report here the results of an attempt at using it for inspecting sequences of verbs from French accounts of road accidents. This analysis comes from an original approach of unsupervised training allowing the discovery of the structure of sequential data. The entries of the analyzer were only made of the verbs appearing in the sentences. It provided a classification of the links between two successive verbs into four distinct clusters, allowing thus text segmentation. We give here an interpretation of these clusters by applying a statistical analysis to independent semantic annotations.