Protein representation learning is a challenging task that aims to capture the structure and function of proteins from their amino acid sequences. Previous methods largely ignored the fact that not all amino acids are equally important for protein folding and activity. In this article, we propose a neural clustering framework that can automatically discover the critical components of a protein by considering both its primary and tertiary structure information. Our framework treats a protein as a graph, where each node represents an amino acid and each edge represents a spatial or sequential connection between amino acids. We then apply an iterative clustering strategy to group the nodes into clusters based on their 1D and 3D positions and assign scores to each cluster. We select the highest-scoring clusters and use their medoid nodes for the next iteration of clustering, until we obtain a hierarchical and informative representation of the protein. We evaluate on four protein-related tasks: protein fold classification, enzyme reaction classification, gene ontology term prediction, and enzyme commission number prediction. Experimental results demonstrate that our method achieves state-of-the-art performance.

Alzheimer's disease is a progressive, debilitating neurodegenerative disease that affects 50 million people globally. Despite this substantial health burden, available treatments for the disease are limited and its fundamental causes remain poorly understood. Previous work has suggested the existence of clinically-meaningful sub-types, which it is suggested may correspond to distinct etiologies, disease courses, and ultimately appropriate treatments. Here, we use unsupervised learning techniques on electronic health records (EHRs) from a cohort of memory disorder patients to characterise heterogeneity in this disease population. Pre-trained embeddings for medical codes as well as transformer-derived Clinical BERT embeddings of free text are used to encode patient EHRs. We identify the existence of sub-populations on the basis of comorbidities and shared textual features, and discuss their clinical significance.

Time series forecasting has attracted significant attention in recent decades. Previous studies have demonstrated that the Channel-Independent (CI) strategy improves forecasting performance by treating different channels individually, while it leads to poor generalization on unseen instances and ignores potentially necessary interactions between channels. Conversely, the Channel-Dependent (CD) strategy mixes all channels with even irrelevant and indiscriminate information, which, however, results in oversmoothing issues and limits forecasting accuracy. There is a lack of channel strategy that effectively balances individual channel treatment for improved forecasting performance without overlooking essential interactions between channels. Motivated by our observation of a correlation between the time series model's performance boost against channel mixing and the intrinsic similarity on a pair of channels, we developed a novel and adaptable Channel Clustering Module (CCM). CCM dynamically groups channels characterized by intrinsic similarities and leverages cluster identity instead of channel identity, combining the best of CD and CI worlds. Extensive experiments on real-world datasets demonstrate that CCM can (1) boost the performance of CI and CD models by an average margin of 2.4% and 7.2% on long-term and short-term forecasting, respectively; (2) enable zero-shot forecasting with mainstream time series forecasting models; (3) uncover intrinsic time series patterns among channels and improve interpretability of complex time series models.

Learning using statistical invariants (LUSI) is a new learning paradigm, which adopts weak convergence mechanism, and can be applied to a wider range of classification problems. However, the computation cost of invariant matrices in LUSI is high for large-scale datasets during training. To settle this issue, this paper introduces a granularity statistical invariant for LUSI, and develops a new learning paradigm called learning using granularity statistical invariants (LUGSI). LUGSI employs both strong and weak convergence mechanisms, taking a perspective of minimizing expected risk. As far as we know, it is the first time to construct granularity statistical invariants. Compared to LUSI, the introduction of this new statistical invariant brings two advantages. Firstly, it enhances the structural information of the data. Secondly, LUGSI transforms a large invariant matrix into a smaller one by maximizing the distance between classes, achieving feasibility for large-scale datasets classification problems and significantly enhancing the training speed of model operations. Experimental results indicate that LUGSI not only exhibits improved generalization capabilities but also demonstrates faster training speed, particularly for large-scale datasets.

Scientific articles are long text documents organized into sections, each describing aspects of the research. Analyzing scientific production has become progressively challenging due to the increase in the number of available articles. Within this scenario, our approach consisted of fine-tuning transformer language models to generate sentence-level embeddings from scientific articles, considering the following labels: background, objective, methods, results, and conclusion. We trained our models on three datasets with contrastive learning. Two datasets are from the article's abstracts in the computer science and medical domains. Also, we introduce PMC-Sents-FULL, a novel dataset of sentences extracted from the full texts of medical articles. We compare the fine-tuned and baseline models in clustering and classification tasks to evaluate our approach. On average, clustering agreement measures values were five times higher. For the classification measures, in the best-case scenario, we had an average improvement in F1-micro of 30.73\%. Results show that fine-tuning sentence transformers with contrastive learning and using the generated embeddings in downstream tasks is a feasible approach to sentence classification in scientific articles. Our experiment codes are available on GitHub.

As the ubiquity of deep learning in various machine learning applications has amplified, a proliferation of neural network models has been trained and shared on public model repositories. In the context of a targeted machine learning assignment, utilizing an apt source model as a starting point typically outperforms the strategy of training from scratch, particularly with limited training data. Despite the investigation and development of numerous model selection strategies in prior work, the process remains time-consuming, especially given the ever-increasing scale of model repositories. In this paper, we propose a two-phase (coarse-recall and fine-selection) model selection framework, aiming to enhance the efficiency of selecting a robust model by leveraging the models' training performances on benchmark datasets. Specifically, the coarse-recall phase clusters models showcasing similar training performances on benchmark datasets in an offline manner. A light-weight proxy score is subsequently computed between this model cluster and the target dataset, which serves to recall a significantly smaller subset of potential candidate models in a swift manner. In the following fine-selection phase, the final model is chosen by fine-tuning the recalled models on the target dataset with successive halving. To accelerate the process, the final fine-tuning performance of each potential model is predicted by mining the model's convergence trend on the benchmark datasets, which aids in filtering lower performance models more earlier during fine-tuning. Through extensive experimentation on tasks covering natural language processing and computer vision, it has been demonstrated that the proposed methodology facilitates the selection of a high-performing model at a rate about 3x times faster than conventional baseline methods. Our code is available at https://github.com/plasware/two-phase-selection.

Bike-sharing systems (BSSs) are deployed in over a thousand cities worldwide and play an important role in many urban transportation systems. BSSs alleviate congestion, reduce pollution and promote physical exercise. It is essential to explore the spatiotemporal patterns of bike-sharing demand, as well as the factors that influence these patterns, in order to optimise system operational efficiency. In this study, an optimised geo-temporal graph is constructed using trip data from Moby Bikes, a dockless BSS operator. The process of optimising the graph unveiled prime locations for erecting new stations during future expansions of the BSS. The Louvain algorithm, a community detection technique, is employed to uncover usage patterns at different levels of temporal granularity. The community detection results reveal largely self-contained sub-networks that exhibit similar usage patterns at their respective levels of temporal granularity. Overall, this study reinforces that BSSs are intrinsically spatiotemporal systems, with community presence driven by spatiotemporal dynamics. These findings may aid operators in improving redistribution efficiency.

In recent years, incomplete multi-view clustering, which studies the challenging multi-view clustering problem on missing views, has received growing research interests. Although a series of methods have been proposed to address this issue, the following problems still exist: 1) Almost all of the existing methods are based on shallow models, which is difficult to obtain discriminative common representations. 2) These methods are generally sensitive to noise or outliers since the negative samples are treated equally as the important samples. In this paper, we propose a novel incomplete multi-view clustering network, called Cognitive Deep Incomplete Multi-view Clustering Network (CDIMC-net), to address these issues. Specifically, it captures the high-level features and local structure of each view by incorporating the view-specific deep encoders and graph embedding strategy into a framework. Moreover, based on the human cognition, i.e., learning from easy to hard, it introduces a self-paced strategy to select the most confident samples for model training, which can reduce the negative influence of outliers. Experimental results on several incomplete datasets show that CDIMC-net outperforms the state-of-the-art incomplete multi-view clustering methods.

The integration of bots in Distributed Ledger Technologies (DLTs) fosters efficiency and automation. However, their use is also associated with predatory trading and market manipulation, and can pose threats to system integrity. It is therefore essential to understand the extent of bot deployment in DLTs; despite this, current detection systems are predominantly rule-based and lack flexibility. In this study, we present a novel approach that utilizes machine learning for the detection of financial bots on the Ethereum platform. First, we systematize existing scientific literature and collect anecdotal evidence to establish a taxonomy for financial bots, comprising 7 categories and 24 subcategories. Next, we create a ground-truth dataset consisting of 133 human and 137 bot addresses. Third, we employ both unsupervised and supervised machine learning algorithms to detect bots deployed on Ethereum. The highest-performing clustering algorithm is a Gaussian Mixture Model with an average cluster purity of 82.6%, while the highest-performing model for binary classification is a Random Forest with an accuracy of 83%. Our machine learning-based detection mechanism contributes to understanding the Ethereum ecosystem dynamics by providing additional insights into the current bot landscape.

This paper studies the directed graph clustering problem through the lens of statistics, where we formulate clustering as estimating underlying communities in the directed stochastic block model (DSBM). We conduct the maximum likelihood estimation (MLE) on the DSBM and thereby ascertain the most probable community assignment given the observed graph structure. In addition to the statistical point of view, we further establish the equivalence between this MLE formulation and a novel flow optimization heuristic, which jointly considers two important directed graph statistics: edge density and edge orientation. Building on this new formulation of directed clustering, we introduce two efficient and interpretable directed clustering algorithms, a spectral clustering algorithm and a semidefinite programming based clustering algorithm. We provide a theoretical upper bound on the number of misclustered vertices of the spectral clustering algorithm using tools from matrix perturbation theory. We compare, both quantitatively and qualitatively, our proposed algorithms with existing directed clustering methods on both synthetic and real-world data, thus providing further ground to our theoretical contributions. Keywords: graph clustering, directed graphs, maximum likelihood estimation, spectral methods, matrix perturbation analysis, semidefinite programming. Authors are listed in alphabetical order. This is the corresponding author.