Mingjun Zhong

Miles Everett, Mingjun Zhong, Georgios Leontidis

Capsule Networks have emerged as a powerful class of deep learning architectures, known for robust performance with relatively few parameters compared to Convolutional Neural Networks (CNNs). However, their inherent efficiency is often overshadowed by their slow, iterative routing mechanisms which establish connections between Capsule layers, posing computational challenges resulting in an inability to scale. In this paper, we introduce a novel, non-iterative routing mechanism, inspired by trainable prototype clustering. This innovative approach aims to mitigate computational complexity, while retaining, if not enhancing, performance efficacy. Furthermore, we harness a shared Capsule subspace, negating the need to project each lower-level Capsule to each higher-level Capsule, thereby significantly reducing memory requisites during training. Our approach demonstrates superior results compared to the current best non-iterative Capsule Network and tests on the Imagewoof dataset, which is too computationally demanding to handle efficiently by iterative approaches. Our findings underscore the potential of our proposed methodology in enhancing the operational efficiency and performance of Capsule Networks, paving the way for their application in increasingly complex computational scenarios. Code is available at https://github.com/mileseverett/ProtoCaps.

Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong

Self-supervised learning algorithms (SSL) based on instance discrimination have shown promising results, performing competitively or even outperforming supervised learning counterparts in some downstream tasks. Such approaches employ data augmentation to create two views of the same instance (i.e., positive pairs) and encourage the model to learn good representations by attracting these views closer in the embedding space without collapsing to the trivial solution. However, data augmentation is limited in representing positive pairs, and the repulsion process between the instances during contrastive learning may discard important features for instances that have similar categories. To address this issue, we propose an approach to identify those images with similar semantic content and treat them as positive instances, thereby reducing the chance of discarding important features during representation learning and increasing the richness of the latent representation. Our approach is generic and could work with any self-supervised instance discrimination frameworks such as MoCo and SimSiam. To evaluate our method, we run experiments on three benchmark datasets: ImageNet, STL-10 and CIFAR-10 with different instance discrimination SSL approaches. The experimental results show that our approach consistently outperforms the baseline methods across all three datasets; for instance, we improve upon the vanilla MoCo-v2 by 4.1% on ImageNet under a linear evaluation protocol over 800 epochs. We also report results on semi-supervised learning, transfer learning on downstream tasks, and object detection.

Miles Everett, Aiden Durrant, Mingjun Zhong et al.

Learning invariant representations has been the long-standing approach to self-supervised learning. However, recently progress has been made in preserving equivariant properties in representations, yet do so with highly prescribed architectures. In this work, we propose an invariant-equivariant self-supervised architecture that employs Capsule Networks (CapsNets), which have been shown to capture equivariance with respect to novel viewpoints. We demonstrate that the use of CapsNets in equivariant self-supervised architectures achieves improved downstream performance on equivariant tasks with higher efficiency and fewer network parameters. To accommodate the architectural changes of CapsNets, we introduce a new objective function based on entropy minimisation. This approach, which we name CapsIE (Capsule Invariant Equivariant Network), achieves state-of-the-art performance on the equivariant rotation tasks on the 3DIEBench dataset compared to prior equivariant SSL methods, while performing competitively against supervised counterparts. Our results demonstrate the ability of CapsNets to learn complex and generalised representations for large-scale, multi-task datasets compared to previous CapsNet benchmarks. Code is available at https://github.com/AberdeenML/CapsIE.

Anthony Mbata, Yaji Sripada, Mingjun Zhong

Currently, a variety of pipeline tools are available for use in data engineering. Data scientists can use these tools to resolve data wrangling issues associated with data and accomplish some data engineering tasks from data ingestion through data preparation to utilization as input for machine learning (ML). Some of these tools have essential built-in components or can be combined with other tools to perform desired data engineering operations. While some tools are wholly or partly commercial, several open-source tools are available to perform expert-level data engineering tasks. This survey examines the broad categories and examples of pipeline tools based on their design and data engineering intentions. These categories are Extract Transform Load/Extract Load Transform (ETL/ELT), pipelines for Data Integration, Ingestion, and Transformation, Data Pipeline Orchestration and Workflow Management, and Machine Learning Pipelines. The survey also provides a broad outline of the utilization with examples within these broad groups and finally, a discussion is presented with case studies indicating the usage of pipeline tools for data engineering. The studies present some first-user application experiences with sample data, some complexities of the applied pipeline, and a summary note of approaches to using these tools to prepare data for machine learning.

Michele DIncecco, Stefano Squartini, Mingjun Zhong

Non-intrusive load monitoring (NILM) is a technique to recover source appliances from only the recorded mains in a household. NILM is unidentifiable and thus a challenge problem because the inferred power value of an appliance given only the mains could not be unique. To mitigate the unidentifiable problem, various methods incorporating domain knowledge into NILM have been proposed and shown effective experimentally. Recently, among these methods, deep neural networks are shown performing best. Arguably, the recently proposed sequence-to-point (seq2point) learning is promising for NILM. However, the results were only carried out on the same data domain. It is not clear if the method could be generalised or transferred to different domains, e.g., the test data were drawn from a different country comparing to the training data. We address this issue in the paper, and two transfer learning schemes are proposed, i.e., appliance transfer learning (ATL) and cross-domain transfer learning (CTL). For ATL, our results show that the latent features learnt by a `complex' appliance, e.g., washing machine, can be transferred to a `simple' appliance, e.g., kettle. For CTL, our conclusion is that the seq2point learning is transferable. Precisely, when the training and test data are in a similar domain, seq2point learning can be directly applied to the test data without fine tuning; when the training and test data are in different domains, seq2point learning needs fine tuning before applying to the test data. Interestingly, we show that only the fully connected layers need fine tuning for transfer learning. Source code can be found at https://github.com/MingjunZhong/transferNILM.

Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong

Contrastive instance discrimination methods outperform supervised learning in downstream tasks such as image classification and object detection. However, these methods rely heavily on data augmentation during representation learning, which can lead to suboptimal results if not implemented carefully. A common augmentation technique in contrastive learning is random cropping followed by resizing. This can degrade the quality of representation learning when the two random crops contain distinct semantic content. To tackle this issue, we introduce LeOCLR (Leveraging Original Images for Contrastive Learning of Visual Representations), a framework that employs a novel instance discrimination approach and an adapted loss function. This method prevents the loss of important semantic features caused by mapping different object parts during representation learning. Our experiments demonstrate that LeOCLR consistently improves representation learning across various datasets, outperforming baseline models. For instance, LeOCLR surpasses MoCo-v2 by 5.1% on ImageNet-1K in linear evaluation and outperforms several other methods on transfer learning and object detection tasks.

Miles Everett, Mingjun Zhong, Georgios Leontidis

We propose Masked Capsule Autoencoders (MCAE), the first Capsule Network that utilises pretraining in a modern self-supervised paradigm, specifically the masked image modelling framework. Capsule Networks have emerged as a powerful alternative to Convolutional Neural Networks (CNNs). They have shown favourable properties when compared to Vision Transformers (ViT), but have struggled to effectively learn when presented with more complex data. This has led to Capsule Network models that do not scale to modern tasks. Our proposed MCAE model alleviates this issue by reformulating the Capsule Network to use masked image modelling as a pretraining stage before finetuning in a supervised manner. Across several experiments and ablations studies we demonstrate that similarly to CNNs and ViTs, Capsule Networks can also benefit from self-supervised pretraining, paving the way for further advancements in this neural network domain. For instance, by pretraining on the Imagenette dataset-consisting of 10 classes of Imagenet-sized images-we achieve state-of-the-art results for Capsule Networks, demonstrating a 9% improvement compared to our baseline model. Thus, we propose that Capsule Networks benefit from and should be trained within a masked image modelling framework, using a novel capsule decoder, to enhance a Capsule Network's performance on realistically sized images.

Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong

Instance discrimination is a self-supervised representation learning paradigm wherein individual instances within a dataset are treated as distinct classes. This is typically achieved by generating two disparate views of each instance by applying stochastic transformations, encouraging the model to learn representations invariant to the common underlying object across these views. While this approach facilitates the acquisition of invariant representations for dataset instances under various handcrafted transformations (e.g., random cropping, colour jittering), an exclusive reliance on such data transformations for achieving invariance may inherently limit the model's generalizability to unseen datasets and diverse downstream tasks. The inherent limitation stems from the fact that the finite set of transformations within the data processing pipeline is unable to encompass the full spectrum of potential data variations. In this study, we provide the technical foundation for leveraging semantic pairs to enhance the generalizability of the model's representation and empirically demonstrate that incorporating semantic pairs mitigates the issue of limited transformation coverage. Specifically, we propose that by exposing the model to semantic pairs (i.e., two instances belonging to the same semantic category), we introduce varied real-world scene contexts, thereby fostering the development of more generalizable object representations. To validate this hypothesis, we constructed and released a novel dataset comprising curated semantic pairs and conducted extensive experimentation to empirically establish that their inclusion enables the model to learn more general representations, ultimately leading to improved performance across diverse downstream tasks.

Miles Everett, Mingjun Zhong, Georgios Leontidis

Capsule Networks, an extension to Neural Networks utilizing vector or matrix representations instead of scalars, were initially developed to create a dynamic parse tree where visual concepts evolve from parts to complete objects. Early implementations of Capsule Networks achieved and maintain state-of-the-art results on various datasets. However, recent studies have revealed shortcomings in the original Capsule Network architecture, notably its failure to construct a parse tree and its susceptibility to vanishing gradients when deployed in deeper networks. This paper extends the investigation to a range of leading Capsule Network architectures, demonstrating that these issues are not confined to the original design. We argue that the majority of Capsule Network research has produced architectures that, while modestly divergent from the original Capsule Network, still retain a fundamentally similar structure. We posit that this inherent design similarity might be impeding the scalability of Capsule Networks. Our study contributes to the broader discussion on improving the robustness and scalability of Capsule Networks.

Zhenyu Lu, Yurong Cheng, Mingjun Zhong et al.

Causal inference is to estimate the causal effect in a causal relationship when intervention is applied. Precisely, in a causal model with binary interventions, i.e., control and treatment, the causal effect is simply the difference between the factual and counterfactual. The difficulty is that the counterfactual may never been obtained which has to be estimated and so the causal effect could only be an estimate. The key challenge for estimating the counterfactual is to identify confounders which effect both outcomes and treatments. A typical approach is to formulate causal inference as a supervised learning problem and so counterfactual could be predicted. Including linear regression and deep learning models, recent machine learning methods have been adapted to causal inference. In this paper, we propose a method to estimate Causal Effect by using Variational Information Bottleneck (CEVIB). The promising point is that VIB is able to naturally distill confounding variables from the data, which enables estimating causal effect by using observational data. We have compared CEVIB to other methods by applying them to three data sets showing that our approach achieved the best performance. We also experimentally showed the robustness of our method.

Shouyong Jiang, Hongru Li, Jinglei Guo et al.

Population-based evolutionary algorithms have great potential to handle multiobjective optimisation problems. However, these algorithms depends largely on problem characteristics, and there is a need to improve their performance for a wider range of problems. References, which are often specified by the decision maker's preference in different forms, are a very effective method to improve the performance of algorithms but have not been fully explored in literature. This paper proposes a novel framework for effective use of references to strengthen algorithms. This framework considers references as search targets which can be adjusted based on the information collected during the search. The proposed framework is combined with new strategies, such as reference adaptation and adaptive local mating, to solve different types of problems. The proposed algorithm is compared with state of the arts on a wide range of problems with diverse characteristics. The comparison and extensive sensitivity analysis demonstrate that the proposed algorithm is competitive and robust across different types of problems studied in this paper.

Oleg Arenz, Mingjun Zhong, Gerhard Neumann

Many methods for machine learning rely on approximate inference from intractable probability distributions. Variational inference approximates such distributions by tractable models that can be subsequently used for approximate inference. Learning sufficiently accurate approximations requires a rich model family and careful exploration of the relevant modes of the target distribution. We propose a method for learning accurate GMM approximations of intractable probability distributions based on insights from policy search by using information-geometric trust regions for principled exploration. For efficient improvement of the GMM approximation, we derive a lower bound on the corresponding optimization objective enabling us to update the components independently. Our use of the lower bound ensures convergence to a stationary point of the original objective. The number of components is adapted online by adding new components in promising regions and by deleting components with negligible weight. We demonstrate on several domains that we can learn approximations of complex, multimodal distributions with a quality that is unmet by previous variational inference methods, and that the GMM approximation can be used for drawing samples that are on par with samples created by state-of-the-art MCMC samplers while requiring up to three orders of magnitude less computational resources.

Hong Tang, Huaming Chen, Ting Li et al.

This paper aims to classify a single PCG recording as normal or abnormal for computer-aided diagnosis. The proposed framework for this challenge has four steps: preprocessing, feature extraction, training and validation. In the preprocessing step, a recording is segmented into four states, i.e., the first heart sound, systolic interval, the second heart sound, and diastolic interval by the Springer Segmentation algorithm. In the feature extraction step, the authors extract 324 features from multi-domains to perform classification. A back propagation neural network is used as predication model. The optimal threshold for distinguishing normal and abnormal is determined by the statistics of model output for both normal and abnormal. The performance of the proposed predictor tested by the six training sets is sensitivity 0.812 and specificity 0.860 (overall accuracy is 0.836). However, the performance reduces to sensitivity 0.807 and specificity 0.829 (overall accuracy is 0.818) for the hidden test set.

Ruosi Wan, Mingjun Zhong, Haoyi Xiong et al.

In statistics and machine learning, approximation of an intractable integration is often achieved by using the unbiased Monte Carlo estimator, but the variances of the estimation are generally high in many applications. Control variates approaches are well-known to reduce the variance of the estimation. These control variates are typically constructed by employing predefined parametric functions or polynomials, determined by using those samples drawn from the relevant distributions. Instead, we propose to construct those control variates by learning neural networks to handle the cases when test functions are complex. In many applications, obtaining a large number of samples for Monte Carlo estimation is expensive, which may result in overfitting when training a neural network. We thus further propose to employ auxiliary random variables induced by the original ones to extend data samples for training the neural networks. We apply the proposed control variates with augmented variables to thermodynamic integration and reinforcement learning. Experimental results demonstrate that our method can achieve significant variance reduction compared with other alternatives.

Chaoyun Zhang, Mingjun Zhong, Zongzuo Wang et al.

Energy disaggregation (a.k.a nonintrusive load monitoring, NILM), a single-channel blind source separation problem, aims to decompose the mains which records the whole house electricity consumption into appliance-wise readings. This problem is difficult because it is inherently unidentifiable. Recent approaches have shown that the identifiability problem could be reduced by introducing domain knowledge into the model. Deep neural networks have been shown to be a promising approach for these problems, but sliding windows are necessary to handle the long sequences which arise in signal processing problems, which raises issues about how to combine predictions from different sliding windows. In this paper, we propose sequence-to-point learning, where the input is a window of the mains and the output is a single point of the target appliance. We use convolutional neural networks to train the model. Interestingly, we systematically show that the convolutional neural networks can inherently learn the signatures of the target appliances, which are automatically added into the model to reduce the identifiability problem. We applied the proposed neural network approaches to real-world household energy data, and show that the methods achieve state-of-the-art performance, improving two standard error measures by 84% and 92%.

Mingjun Zhong, Nigel Goddard, Charles Sutton

In many statistical problems, a more coarse-grained model may be suitable for population-level behaviour, whereas a more detailed model is appropriate for accurate modelling of individual behaviour. This raises the question of how to integrate both types of models. Methods such as posterior regularization follow the idea of generalized moment matching, in that they allow matching expectations between two models, but sometimes both models are most conveniently expressed as latent variable models. We propose latent Bayesian melding, which is motivated by averaging the distributions over populations statistics of both the individual-level and the population-level models under a logarithmic opinion pool framework. In a case study on electricity disaggregation, which is a type of single-channel blind source separation problem, we show that latent Bayesian melding leads to significantly more accurate predictions than an approach based solely on generalized moment matching.

Mingjun Zhong, Rong Liu, Bo Liu

MicroRNAs (miRNAs) are small RNA molecules composed of 19-22 nt, which play important regulatory roles in post-transcriptional gene regulation by inhibiting the translation of the mRNA into proteins or otherwise cleaving the target mRNA. Inferring miRNA targets provides useful information for understanding the roles of miRNA in biological processes that are potentially involved in complex diseases. Statistical methodologies for point estimation, such as the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm, have been proposed to identify the interactions of miRNA and mRNA based on sequence and expression data. In this paper, we propose using the Bayesian LASSO (BLASSO) and the non-negative Bayesian LASSO (nBLASSO) to analyse the interactions between miRNA and mRNA using expression data. The proposed Bayesian methods explore the posterior distributions for those parameters required to model the miRNA-mRNA interactions. These approaches can be used to observe the inferred effects of the miRNAs on the targets by plotting the posterior distributions of those parameters. For comparison purposes, the Least Squares Regression (LSR), Ridge Regression (RR), LASSO, non-negative LASSO (nLASSO), and the proposed Bayesian approaches were applied to four public datasets. We concluded that nLASSO and nBLASSO perform best in terms of sensitivity and specificity. Compared to the point estimate algorithms, which only provide single estimates for those parameters, the Bayesian methods are more meaningful and provide credible intervals, which take into account the uncertainty of the inferred interactions of the miRNA and mRNA. Furthermore, Bayesian methods naturally provide statistical significance to select convincing inferred interactions, while point estimate algorithms require a manually chosen threshold, which is less meaningful, to choose the possible interactions.

Mingjun Zhong, Mark Girolami

We present a Bayesian scheme for the approximate diagonalisation of several square matrices which are not necessarily symmetric. A Gibbs sampler is derived to simulate samples of the common eigenvectors and the eigenvalues for these matrices. Several synthetic examples are used to illustrate the performance of the proposed Gibbs sampler and we then provide comparisons to several other joint diagonalization algorithms, which shows that the Gibbs sampler achieves the state-of-the-art performance on the examples considered. As a byproduct, the output of the Gibbs sampler could be used to estimate the log marginal likelihood, however we employ the approximation based on the Bayesian information criterion (BIC) which in the synthetic examples considered correctly located the number of common eigenvectors. We then succesfully applied the sampler to the source separation problem as well as the common principal component analysis and the common spatial pattern analysis problems.