Detecting abrupt changes in data distribution is one of the most significant tasks in streaming data analysis. Although many unsupervised Change-Point Detection (CPD) methods have been proposed recently to identify those changes, they still suffer from missing subtle changes, poor scalability, or/and sensitive to noise points. To meet these challenges, we are the first to generalise the CPD problem as a special case of the Change-Interval Detection (CID) problem. Then we propose a CID method, named iCID, based on a recent Isolation Distributional Kernel (IDK). iCID identifies the change interval if there is a high dissimilarity score between two non-homogeneous temporal adjacent intervals. The data-dependent property and finite feature map of IDK enabled iCID to efficiently identify various types of change points in data streams with the tolerance of noise points. Moreover, the proposed online and offline versions of iCID have the ability to optimise key parameter settings. The effectiveness and efficiency of iCID have been systematically verified on both synthetic and real-world datasets.

This paper describes experiments showing that some tasks in natural language processing (NLP) can already be performed using quantum computers, though so far only with small datasets. We demonstrate various approaches to topic classification. The first uses an explicit word-based approach, in which word-topic scoring weights are implemented as fractional rotations of individual qubit, and a new phrase is classified based on the accumulation of these weights in a scoring qubit using entangling controlled-NOT gates. This is compared with more scalable quantum encodings of word embedding vectors, which are used in the computation of kernel values in a quantum support vector machine: this approach achieved an average of 62% accuracy on classification tasks involving over 10000 words, which is the largest such quantum computing experiment to date. We describe a quantum probability approach to bigram modeling that can be applied to sequences of words and formal concepts, investigating a generative approximation to these distributions using a quantum circuit Born machine, and an approach to ambiguity resolution in verb-noun composition using single-qubit rotations for simple nouns and 2-qubit controlled-NOT gates for simple verbs. The smaller systems described have been run successfully on physical quantum computers, and the larger ones have been simulated. We show that statistically meaningful results can be obtained using real datasets, but this is much more difficult to predict than with easier artificial language examples used previously in developing quantum NLP systems. Other approaches to quantum NLP are compared, partly with respect to contemporary issues including informal language, fluency, and truthfulness.

This paper describes a novel method of training a semantic segmentation model for scene recognition of agricultural mobile robots exploiting publicly available datasets of outdoor scenes that are different from the target greenhouse environments. Semantic segmentation models require abundant labels given by tedious manual annotation. A method to work around it is unsupervised domain adaptation (UDA) that transfers knowledge from labeled source datasets to unlabeled target datasets. However, the effectiveness of existing methods is not well studied in adaptation between heterogeneous environments, such as urban scenes and greenhouses. In this paper, we propose a method to train a semantic segmentation model for greenhouse images without manually labeled datasets of greenhouse images. The core of our idea is to use multiple rich image datasets of different environments with segmentation labels to generate pseudo-labels for the target images to effectively transfer the knowledge from multiple sources and realize a precise training of semantic segmentation. Along with the pseudo-label generation, we introduce state-of-the-art methods to deal with noise in the pseudo-labels to further improve the performance. We demonstrate in experiments with multiple greenhouse datasets that our proposed method improves the performance compared to the single-source baselines and an existing approach.

We focus on the problem of learning without forgetting from multiple tasks arriving sequentially, where each task is defined using a few-shot episode of novel or already seen classes. We approach this problem using the recently published HyperTransformer (HT), a Transformer-based hypernetwork that generates specialized task-specific CNN weights directly from the support set. In order to learn from a continual sequence of tasks, we propose to recursively re-use the generated weights as input to the HT for the next task. This way, the generated CNN weights themselves act as a representation of previously learned tasks, and the HT is trained to update these weights so that the new task can be learned without forgetting past tasks. This approach is different from most continual learning algorithms that typically rely on using replay buffers, weight regularization or task-dependent architectural changes. We demonstrate that our proposed Continual HyperTransformer method equipped with a prototypical loss is capable of learning and retaining knowledge about past tasks for a variety of scenarios, including learning from mini-batches, and task-incremental and class-incremental learning scenarios.

We consider a semi-supervised $k$-clustering problem where information is available on whether pairs of objects are in the same or in different clusters. This information is either available with certainty or with a limited level of confidence. We introduce the PCCC algorithm, which iteratively assigns objects to clusters while accounting for the information provided on the pairs of objects. Our algorithm can include relationships as hard constraints that are guaranteed to be satisfied or as soft constraints that can be violated subject to a penalty. This flexibility distinguishes our algorithm from the state-of-the-art in which all pairwise constraints are either considered hard, or all are considered soft. Unlike existing algorithms, our algorithm scales to large-scale instances with up to 60,000 objects, 100 clusters, and millions of cannot-link constraints (which are the most challenging constraints to incorporate). We compare the PCCC algorithm with state-of-the-art approaches in an extensive computational study. Even though the PCCC algorithm is more general than the state-of-the-art approaches in its applicability, it outperforms the state-of-the-art approaches on instances with all hard constraints or all soft constraints both in terms of running time and various metrics of solution quality. The source code of the PCCC algorithm is publicly available on GitHub.

We study to what extent may stochastic gradient descent (SGD) be understood as a "conventional" learning rule that achieves generalization performance by obtaining a good fit to training data. We consider the fundamental stochastic convex optimization framework, where (one pass, without-replacement) SGD is classically known to minimize the population risk at rate $O(1/\sqrt n)$, and prove that, surprisingly, there exist problem instances where the SGD solution exhibits both empirical risk and generalization gap of $\Omega(1)$. Consequently, it turns out that SGD is not algorithmically stable in any sense, and its generalization ability cannot be explained by uniform convergence or any other currently known generalization bound technique for that matter (other than that of its classical analysis). We then continue to analyze the closely related with-replacement SGD, for which we show that an analogous phenomenon does not occur and prove that its population risk does in fact converge at the optimal rate. Finally, we interpret our main results in the context of without-replacement SGD for finite-sum convex optimization problems, and derive upper and lower bounds for the multi-epoch regime that significantly improve upon previously known results.

Consider each node of a graph to be generating a data stream that is synchronized and observed at near real-time. At a change-point $\tau$, a change occurs at a subset of nodes $C$, which affects the probability distribution of their associated node streams. In this paper, we propose a novel kernel-based method to both detect $\tau$ and localize $C$, based on the direct estimation of the likelihood-ratio between the post-change and the pre-change distributions of the node streams. Our main working hypothesis is the smoothness of the likelihood-ratio estimates over the graph, i.e connected nodes are expected to have similar likelihood-ratios. The quality of the proposed method is demonstrated on extensive experiments on synthetic scenarios.

The mining and exploitation of graph structural information have been the focal points in the study of complex networks. Traditional structural measures in Network Science focus on the analysis and modelling of complex networks from the perspective of network structure, such as the centrality measures, the clustering coefficient, and motifs and graphlets, and they have become basic tools for studying and understanding graphs. In comparison, graph neural networks, especially graph convolutional networks (GCNs), are particularly effective at integrating node features into graph structures via neighbourhood aggregation and message passing, and have been shown to significantly improve the performances in a variety of learning tasks. These two classes of methods are, however, typically treated separately with limited references to each other. In this work, aiming to establish relationships between them, we provide a network science perspective of GCNs. Our novel taxonomy classifies GCNs from three structural information angles, i.e., the layer-wise message aggregation scope, the message content, and the overall learning scope. Moreover, as a prerequisite for reviewing GCNs via a network science perspective, we also summarise traditional structural measures and propose a new taxonomy for them. Finally and most importantly, we draw connections between traditional structural approaches and graph convolutional networks, and discuss potential directions for future research.

L2 regularization is a method used to prevent overfitting in machine learning models. It adds a penalty term to the loss function that is proportional to the sum of the squares of the weights. This penalizes large weights and encourages the model to use only the most relevant features. L2 regularization is also known as weight decay because it causes the model's weight to decay toward zero. The penalty term is usually added to the loss function during training and is typically set by cross-validation.

Abstract: Principal component analysis (PCA) plays an important role in the analysis of cryo-EM images for various tasks such as classification, denoising, compression, and ab-initio modeling. We introduce a fast method for estimating a compressed representation of the 2-D covariance matrix of noisy cryo-electron microscopy projection images that enables fast PCA computation. Our method is based on a new algorithm for expanding images in the Fourier-Bessel basis (the harmonics on the disk), which provides a convenient way to handle the effect of the contrast transfer functions. For N images of size L L, our method has time complexity O(NL3 L4) and space complexity O(NL2 L3). In contrast to previous work, these complexities are independent of the number of different contrast transfer functions of the images.