Danilo P. Mandic

Yichong Leng, Zehua Chen, Junliang Guo et al. · microsoft-research

Binaural audio plays a significant role in constructing immersive augmented and virtual realities. As it is expensive to record binaural audio from the real world, synthesizing them from mono audio has attracted increasing attention. This synthesis process involves not only the basic physical warping of the mono audio, but also room reverberations and head/ear related filtrations, which, however, are difficult to accurately simulate in traditional digital signal processing. In this paper, we formulate the synthesis process from a different perspective by decomposing the binaural audio into a common part that shared by the left and right channels as well as a specific part that differs in each channel. Accordingly, we propose BinauralGrad, a novel two-stage framework equipped with diffusion models to synthesize them respectively. Specifically, in the first stage, the common information of the binaural audio is generated with a single-channel diffusion model conditioned on the mono audio, based on which the binaural audio is generated by a two-channel diffusion model in the second stage. Combining this novel perspective of two-stage synthesis with advanced generative models (i.e., the diffusion models),the proposed BinauralGrad is able to generate accurate and high-fidelity binaural audio samples. Experiment results show that on a benchmark dataset, BinauralGrad outperforms the existing baselines by a large margin in terms of both object and subject evaluation metrics (Wave L2: 0.128 vs. 0.157, MOS: 3.80 vs. 3.61). The generated audio samples (https://speechresearch.github.io/binauralgrad) and code (https://github.com/microsoft/NeuralSpeech/tree/master/BinauralGrad) are available online.

Haohe Liu, Zehua Chen, Yi Yuan et al.

Text-to-audio (TTA) system has recently gained attention for its ability to synthesize general audio based on text descriptions. However, previous studies in TTA have limited generation quality with high computational costs. In this study, we propose AudioLDM, a TTA system that is built on a latent space to learn the continuous audio representations from contrastive language-audio pretraining (CLAP) latents. The pretrained CLAP models enable us to train LDMs with audio embedding while providing text embedding as a condition during sampling. By learning the latent representations of audio signals and their compositions without modeling the cross-modal relationship, AudioLDM is advantageous in both generation quality and computational efficiency. Trained on AudioCaps with a single GPU, AudioLDM achieves state-of-the-art TTA performance measured by both objective and subjective metrics (e.g., frechet distance). Moreover, AudioLDM is the first TTA system that enables various text-guided audio manipulations (e.g., style transfer) in a zero-shot fashion. Our implementation and demos are available at https://audioldm.github.io.

Anh-Huy Phan, Andrzej Cichocki, Andre Uschmajew et al.

Decompositions of tensors into factor matrices, which interact through a core tensor, have found numerous applications in signal processing and machine learning. A more general tensor model which represents data as an ordered network of sub-tensors of order-2 or order-3 has, so far, not been widely considered in these fields, although this so-called tensor network decomposition has been long studied in quantum physics and scientific computing. In this study, we present novel algorithms and applications of tensor network decompositions, with a particular focus on the tensor train decomposition and its variants. The novel algorithms developed for the tensor train decomposition update, in an alternating way, one or several core tensors at each iteration, and exhibit enhanced mathematical tractability and scalability to exceedingly large-scale data tensors. The proposed algorithms are tested in classic paradigms of blind source separation from a single mixture, denoising, and feature extraction, and achieve superior performance over the widely used truncated algorithms for tensor train decomposition.

Chuang Liu, Xueqi Ma, Yibing Zhan et al.

Graph Neural Networks (GNNs) tend to suffer from high computation costs due to the exponentially increasing scale of graph data and the number of model parameters, which restricts their utility in practical applications. To this end, some recent works focus on sparsifying GNNs with the lottery ticket hypothesis (LTH) to reduce inference costs while maintaining performance levels. However, the LTH-based methods suffer from two major drawbacks: 1) they require exhaustive and iterative training of dense models, resulting in an extremely large training computation cost, and 2) they only trim graph structures and model parameters but ignore the node feature dimension, where significant redundancy exists. To overcome the above limitations, we propose a comprehensive graph gradual pruning framework termed CGP. This is achieved by designing a during-training graph pruning paradigm to dynamically prune GNNs within one training process. Unlike LTH-based methods, the proposed CGP approach requires no re-training, which significantly reduces the computation costs. Furthermore, we design a co-sparsifying strategy to comprehensively trim all three core elements of GNNs: graph structures, node features, and model parameters. Meanwhile, aiming at refining the pruning operation, we introduce a regrowth process into our CGP framework, in order to re-establish the pruned but important connections. The proposed CGP is evaluated by using a node classification task across 6 GNN architectures, including shallow models (GCN and GAT), shallow-but-deep-propagation models (SGC and APPNP), and deep models (GCNII and ResGCN), on a total of 14 real-world graph datasets, including large-scale graph datasets from the challenging Open Graph Benchmark. Experiments reveal that our proposed strategy greatly improves both training and inference efficiency while matching or even exceeding the accuracy of existing methods.

Zehua Chen, Yihan Wu, Yichong Leng et al.

Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples. However, their iterative refinement process in high-dimensional data space results in slow inference speed, which restricts their application in real-time systems. Previous works have explored speeding up by minimizing the number of inference steps but at the cost of sample quality. In this work, to improve the inference speed for DDPM-based TTS model while achieving high sample quality, we propose ResGrad, a lightweight diffusion model which learns to refine the output spectrogram of an existing TTS model (e.g., FastSpeech 2) by predicting the residual between the model output and the corresponding ground-truth speech. ResGrad has several advantages: 1) Compare with other acceleration methods for DDPM which need to synthesize speech from scratch, ResGrad reduces the complexity of task by changing the generation target from ground-truth mel-spectrogram to the residual, resulting into a more lightweight model and thus a smaller real-time factor. 2) ResGrad is employed in the inference process of the existing TTS model in a plug-and-play way, without re-training this model. We verify ResGrad on the single-speaker dataset LJSpeech and two more challenging datasets with multiple speakers (LibriTTS) and high sampling rate (VCTK). Experimental results show that in comparison with other speed-up methods of DDPMs: 1) ResGrad achieves better sample quality with the same inference speed measured by real-time factor; 2) with similar speech quality, ResGrad synthesizes speech faster than baseline methods by more than 10 times. Audio samples are available at https://resgrad1.github.io/.

Shengxi Li, Xinyi Zhao, Ljubisa Stankovic et al.

The success of convolution neural networks (CNN) has been revolutionising the way we approach and use intelligent machines in the Big Data era. Despite success, CNNs have been consistently put under scrutiny owing to their \textit{black-box} nature, an \textit{ad hoc} manner of their construction, together with the lack of theoretical support and physical meanings of their operation. This has been prohibitive to both the quantitative and qualitative understanding of CNNs, and their application in more sensitive areas such as AI for health. We set out to address these issues, and in this way demystify the operation of CNNs, by employing the perspective of matched filtering. We first illuminate that the convolution operation, the very core of CNNs, represents a matched filter which aims to identify the presence of features in input data. This then serves as a vehicle to interpret the convolution-activation-pooling chain in CNNs under the theoretical umbrella of matched filtering, a common operation in signal processing. We further provide extensive examples and experiments to illustrate this connection, whereby the learning in CNNs is shown to also perform matched filtering, which further sheds light onto physical meaning of learnt parameters and layers. It is our hope that this material will provide new insights into the understanding, constructing and analysing of CNNs, as well as paving the way for developing new methods and architectures of CNNs.

Min Xiang, Shirin Enshaeifar, Alexander E. Stott et al.

Recent developments in quaternion-valued widely linear processing have established that the exploitation of complete second-order statistics requires consideration of both the standard covariance and the three complementary covariance matrices. Although such matrices have a tremendous amount of structure and their decomposition is a powerful tool in a variety of applications, the non-commutative nature of the quaternion product has been prohibitive to the development of quaternion uncorrelating transforms. To this end, we introduce novel techniques for a simultaneous decomposition of the covariance and complementary covariance matrices in the quaternion domain, whereby the quaternion version of the Takagi factorisation is explored to diagonalise symmetric quaternion-valued matrices. This gives new insights into the quaternion uncorrelating transform (QUT) and forms a basis for the proposed quaternion approximate uncorrelating transform (QAUT) which simultaneously diagonalises all four covariance matrices associated with improper quaternion signals. The effectiveness of the proposed uncorrelating transforms is validated by simulations on both synthetic and real-world quaternion-valued signals.

Sithan Kanna, Dahir H. Dini, Yili Xia et al.

A novel method for distributed estimation of the frequency of power systems is introduced based on the cooperation between multiple measurement nodes. The proposed distributed widely linear complex Kalman filter (D-ACKF) and the distributed widely linear extended complex Kalman filter (D-AECKF) employ a widely linear state space and augmented complex statistics to deal with unbalanced system conditions and the generality complex signals, both second order circular (proper) and second order noncircular (improper). It is shown that the current, strictly linear, estimators are inadequate for unbalanced systems, a typical case in smart grids, as they do not account for either the noncircularity of Clarke's αβ-voltage in unbalanced conditions or the correlated nature of nodal disturbances. We illuminate the relationship between the degree of circularity of Clarke's voltage and system imbalance, and prove that the proposed widely linear estimators are optimal for such conditions, while also accounting for the correlated and noncircular nature of real-world nodal disturbances. {Synthetic and real world} case studies over a range of power system conditions illustrate the theoretical and practical advantages of the proposed methodology.

Alexander Jenkins, Imad Jaimoukha, Ljubisa Stankovic et al.

Forming the right combination of students in a group promises to enable a powerful and effective environment for learning and collaboration. However, defining a group of students is a complex task which has to satisfy multiple constraints. This work introduces an unsupervised algorithm for fair and skill-diverse student group formation. This is achieved by taking account of student course marks and sensitive attributes provided by the education office. The skill sets of students are determined using unsupervised dimensionality reduction of course mark data via the Laplacian eigenmap. The problem is formulated as a constrained graph partitioning problem, whereby the diversity of skill sets in each group are maximised, group sizes are upper and lower bounded according to available resources, and `balance' of a sensitive attribute is lower bounded to enforce fairness in group formation. This optimisation problem is solved using integer programming and its effectiveness is demonstrated on a dataset of student course marks from Imperial College London.

Dongpo Xu, Jinlan Liu, Yinghua Lu et al.

The stochastic momentum method is a commonly used acceleration technique for solving large-scale stochastic optimization problems in artificial neural networks. Current convergence results of stochastic momentum methods under non-convex stochastic settings mostly discuss convergence in terms of the random output and minimum output. To this end, we address the convergence of the last iterate output (called last-iterate convergence) of the stochastic momentum methods for non-convex stochastic optimization problems, in a way conformal with traditional optimization theory. We prove the last-iterate convergence of the stochastic momentum methods under a unified framework, covering both stochastic heavy ball momentum and stochastic Nesterov accelerated gradient momentum. The momentum factors can be fixed to be constant, rather than time-varying coefficients in existing analyses. Finally, the last-iterate convergence of the stochastic momentum methods is verified on the benchmark MNIST and CIFAR-10 datasets.

Danilo P. Mandic, Sayed Pouria Talebi, Clive Cheong Took et al.

From their inception, quaternions and their division algebra have proven to be advantageous in modelling rotation/orientation in three-dimensional spaces and have seen use from the initial formulation of electromagnetic filed theory through to forming the basis of quantum filed theory. Despite their impressive versatility in modelling real-world phenomena, adaptive information processing techniques specifically designed for quaternion-valued signals have only recently come to the attention of the machine learning, signal processing, and control communities. The most important development in this direction is introduction of the HR-calculus, which provides the required mathematical foundation for deriving adaptive information processing techniques directly in the quaternion domain. In this article, the foundations of the HR-calculus are revised and the required tools for deriving adaptive learning techniques suitable for dealing with quaternion-valued signals, such as the gradient operator, chain and product derivative rules, and Taylor series expansion are presented. This serves to establish the most important applications of adaptive information processing in the quaternion domain for both single-node and multi-node formulations. The article is supported by Supplementary Material, which will be referred to as SM.

Xueqi Ma, Xingjun Ma, Sarah Monazam Erfani et al.

Developing open-set classification methods capable of classifying in-distribution (ID) data while detecting out-of-distribution (OOD) samples is essential for deploying graph neural networks (GNNs) in open-world scenarios. Existing methods typically treat all OOD samples as a single class, despite real-world applications, especially high-stake settings such as fraud detection and medical diagnosis, demanding deeper insights into OOD samples, including their probable labels. This raises a critical question: can OOD detection be extended to OOD classification without true label information? To address this question, we propose a Coarse-to-Fine open-set Classification (CFC) framework that leverages large language models (LLMs) for graph datasets. CFC consists of three key components: a coarse classifier that uses LLM prompts for OOD detection and outlier label generation, a GNN-based fine classifier trained with OOD samples identified by the coarse classifier for enhanced OOD detection and ID classification, and refined OOD classification achieved through LLM prompts and post-processed OOD labels. Unlike methods that rely on synthetic or auxiliary OOD samples, CFC employs semantic OOD instances that are genuinely out-of-distribution based on their inherent meaning, improving interpretability and practical utility. Experimental results show that CFC improves OOD detection by ten percent over state-of-the-art methods on graph and text domains and achieves up to seventy percent accuracy in OOD classification on graph datasets.

Sayed Pouria Talebi, Danilo Mandic

Multiagent systems aim to accomplish highly complex learning tasks through decentralised consensus seeking dynamics and their use has garnered a great deal of attention in the signal processing and computational intelligence societies. This article examines the behaviour of multiagent networked systems with nonlinear filtering/learning dynamics. To this end, a general formulation for the actions of an agent in multiagent networked systems is presented and conditions for achieving a cohesive learning behaviour is given. Importantly, application of the so derived framework in distributed and federated learning scenarios are presented.

Yao Lei Xu, Kriton Konstantinidis, Danilo P. Mandic

Despite the omnipresence of tensors and tensor operations in modern deep learning, the use of tensor mathematics to formally design and describe neural networks is still under-explored within the deep learning community. To this end, we introduce the Graph Tensor Network (GTN) framework, an intuitive yet rigorous graphical framework for systematically designing and implementing large-scale neural learning systems on both regular and irregular domains. The proposed framework is shown to be general enough to include many popular architectures as special cases, and flexible enough to handle data on any and many data domains. The power and flexibility of the proposed framework is demonstrated through real-data experiments, resulting in improved performance at a drastically lower complexity costs, by virtue of tensor algebra.

Harry J. Davies, James Monsen, Danilo P. Mandic

Decoder-only transformers are the backbone of the popular generative pre-trained transformer (GPT) series of large language models. In this work, we employ this framework to the analysis of clinical heart time-series data, to create two pre-trained general purpose cardiac models, termed PPG-PT and ECG-PT. We place a special emphasis on making both such pre-trained models fully interpretable. This is achieved firstly through aggregate attention maps which show that, in order to make predictions, the model focuses on similar points in previous cardiac cycles and gradually broadens its attention in deeper layers. Next, we show that tokens with the same value, which occur at different distinct points in the electrocardiography (ECG) and photoplethysmography (PPG) cycle, form separate clusters in high dimensional space. The clusters form according to phase, as the tokens propagate through the transformer blocks. Finally, we highlight that individual attention heads respond to specific physiologically relevent features, such as the dicrotic notch in PPG and the P-wave in ECG. It is also demonstrated that these pre-trained models are straightforward to fine-tune for tasks such as classification of atrial fibrillation (AF), and beat detection in photoplethysmography. For the example of AF, the fine-tuning took 11 minutes of computer time, and achieved the respective leave-one-subject-out AUCs of 0.99 and 0.93 for ECG and PPG within the MIMIC Perform AF dataset. In addition, the fine-tuned beat detector achieved a state-of-the-art F1 score of 98%, as well as uniquely providing a beat confidence level which acts as a signal quality estimator. Importantly, the fine-tuned models for AF screening are also fully explainable, with attention shifting to regions in the context that are strongly indicative of atrial fibrillation.

Harry J. Davies, Danilo P. Mandic

Much of the information of breathing is contained within the photoplethysmography (PPG) signal, through changes in venous blood flow, heart rate and stroke volume. We aim to leverage this fact, by employing a novel deep learning framework which is a based on a repurposed convolutional autoencoder. Our model aims to encode all of the relevant respiratory information contained within photoplethysmography waveform, and decode it into a waveform that is similar to a gold standard respiratory reference. The model is employed on two photoplethysmography data sets, namely Capnobase and BIDMC. We show that the model is capable of producing respiratory waveforms that approach the gold standard, while in turn producing state of the art respiratory rate estimates. We also show that when it comes to capturing more advanced respiratory waveform characteristics such as duty cycle, our model is for the most part unsuccessful. A suggested reason for this, in light of a previous study on in-ear PPG, is that the respiratory variations in finger-PPG are far weaker compared with other recording locations. Importantly, our model can perform these waveform estimates in a fraction of a millisecond, giving it the capacity to produce over 6 hours of respiratory waveforms in a single second. Moreover, we attempt to interpret the behaviour of the kernel weights within the model, showing that in part our model intuitively selects different breathing frequencies. The model proposed in this work could help to improve the usefulness of consumer PPG-based wearables for medical applications, where detailed respiratory information is required.

Alexander Jenkins, Zehua Chen, Fu Siong Ng et al.

Pulsative signals such as the electrocardiogram (ECG) are extensively collected as part of routine clinical care. However, noisy and poor-quality recordings are a major issue for signals collected using mobile health systems, decreasing the signal quality, leading to missing values, and affecting automated downstream tasks. Recent studies have explored the imputation of missing values in ECG with probabilistic time-series models. Nevertheless, in comparison with the deterministic models, their performance is still limited, as the variations across subjects and heart-beat relationships are not explicitly considered in the training objective. In this work, to improve the imputation and forecasting accuracy for ECG with probabilistic models, we present a template-guided denoising diffusion probabilistic model (DDPM), PulseDiff, which is conditioned on an informative prior for a range of health conditions. Specifically, 1) we first extract a subject-level pulsative template from the observed values to use as an informative prior of the missing values, which personalises the prior; 2) we then add beat-level stochastic shift terms to augment the prior, which considers variations in the position and amplitude of the prior at each beat; 3) we finally design a confidence score to consider the health condition of the subject, which ensures our prior is provided safely. Experiments with the PTBXL dataset reveal that PulseDiff improves the performance of two strong DDPM baseline models, CSDI and SSSD$^{S4}$, verifying that our method guides the generation of DDPMs while managing the uncertainty. When combined with SSSD$^{S4}$, PulseDiff outperforms the leading deterministic model for short-interval missing data and is comparable for long-interval data loss.

Edoardo Occhipinti, Marek Zylinski, Harry J. Davies et al.

The cardiac dipole has been shown to propagate to the ears, now a common site for consumer wearable electronics, enabling the recording of electrocardiogram (ECG) signals. However, in-ear ECG recordings often suffer from significant noise due to their small amplitude and the presence of other physiological signals, such as electroencephalogram (EEG), which complicates the extraction of cardiovascular features. This study addresses this issue by developing a denoising convolutional autoencoder (DCAE) to enhance ECG information from in-ear recordings, producing cleaner ECG outputs. The model is evaluated using a dataset of in-ear ECGs and corresponding clean Lead I ECGs from 45 healthy participants. The results demonstrate a substantial improvement in signal-to-noise ratio (SNR), with a median increase of 5.9 dB. Additionally, the model significantly improved heart rate estimation accuracy, reducing the mean absolute error by almost 70% and increasing R-peak detection precision to a median value of 90%. We also trained and validated the model using a synthetic dataset, generated from real ECG signals, including abnormal cardiac morphologies, corrupted by pink noise. The results obtained show effective removal of noise sources with clinically plausible waveform reconstruction ability.

Yuyang Miao, Yao Xu, Danilo Mandic

Predicting metro passenger flow precisely is of great importance for dynamic traffic planning. Deep learning algorithms have been widely applied due to their robust performance in modelling non-linear systems. However, traditional deep learning algorithms completely discard the inherent graph structure within the metro system. Graph-based deep learning algorithms could utilise the graph structure but raise a few challenges, such as how to determine the weights of the edges and the shallow receptive field caused by the over-smoothing issue. To further improve these challenges, this study proposes a model based on GraphSAGE with an edge weights learner applied. The edge weights learner utilises socially meaningful features to generate edge weights. Hypergraph and temporal exploitation modules are also constructed as add-ons for better performance. A comparison study is conducted on the proposed algorithm and other state-of-art graph neural networks, where the proposed algorithm could improve the performance.

Mingxue Xu, Yao Lei Xu, Danilo P. Mandic

High-dimensional token embeddings underpin Large Language Models (LLMs), as they can capture subtle semantic information and significantly enhance the modelling of complex language patterns. However, this high dimensionality also introduces considerable model parameters and prohibitively high model storage and memory requirements, which is particularly unaffordable for low-end devices. Targeting no extra training data and insufficient computation cases, we propose a training-free model compression approach based on the Tensor-Train Decomposition (TTD), whereby each pre-trained token embedding is converted into a lower-dimensional Matrix Product State (MPS). We then comprehensively investigate the low-rank structures extracted by this approach, in terms of the compression ratio, the language task performance, and latency on a typical low-end device (i.e. Raspberry Pi). Taking GPT family models (i.e. GPT-2 and CerebrasGPT) as case studies, our approach theoretically results in $46.89\%$ fewer parameters of the entire model, with a compression ratio $39.38\times$ - $65.64\times$ for the embedding layers. With different hyperparameter choices, the model compressed with our approach can achieve a comparable language task performance to the original model with around $2.0\times$ embedding layer compression. This empirically proves the existence of low-rank structure in GPT family models, and demonstrates that about half of the parameters in the embedding layers are redundant.

Yao Lei Xu, Kriton Konstantinidis, Danilo P. Mandic

Analytics of financial data is inherently a Big Data paradigm, as such data are collected over many assets, asset classes, countries, and time periods. This represents a challenge for modern machine learning models, as the number of model parameters needed to process such data grows exponentially with the data dimensions; an effect known as the Curse-of-Dimensionality. Recently, Tensor Decomposition (TD) techniques have shown promising results in reducing the computational costs associated with large-dimensional financial models while achieving comparable performance. However, tensor models are often unable to incorporate the underlying economic domain knowledge. To this end, we develop a novel Graph-Regularized Tensor Regression (GRTR) framework, whereby knowledge about cross-asset relations is incorporated into the model in the form of a graph Laplacian matrix. This is then used as a regularization tool to promote an economically meaningful structure within the model parameters. By virtue of tensor algebra, the proposed framework is shown to be fully interpretable, both coefficient-wise and dimension-wise. The GRTR model is validated in a multi-way financial forecasting setting and compared against competing models, and is shown to achieve improved performance at reduced computational costs. Detailed visualizations are provided to help the reader gain an intuitive understanding of the employed tensor operations.

Pauline Bourigault, Danilo P. Mandic

We present a novel approach to anomaly detection by integrating Generalized Hyperbolic (GH) processes into kernel-based methods. The GH distribution, known for its flexibility in modeling skewness, heavy tails, and kurtosis, helps to capture complex patterns in data that deviate from Gaussian assumptions. We propose a GH-based kernel function and utilize it within Kernel Density Estimation (KDE) and One-Class Support Vector Machines (OCSVM) to develop anomaly detection frameworks. Theoretical results confirmed the positive semi-definiteness and consistency of the GH-based kernel, ensuring its suitability for machine learning applications. Empirical evaluation on synthetic and real-world datasets showed that our method improves detection performance in scenarios involving heavy-tailed and asymmetric or imbalanced distributions. https://github.com/paulinebourigault/GHKernelAnomalyDetect

Rohan Tangri, Danilo P. Mandic, Anthony G. Constantinides

Reinforcement learning is increasingly finding success across domains where the problem can be represented as a Markov decision process. Evolutionary computation algorithms have also proven successful in this domain, exhibiting similar performance to the generally more complex reinforcement learning. Whilst there exist many open-source reinforcement learning and evolutionary computation libraries, no publicly available library combines the two approaches for enhanced comparison, cooperation, or visualization. To this end, we have created Pearl (https://github.com/LondonNode/Pearl), an open source Python library designed to allow researchers to rapidly and conveniently perform optimized reinforcement learning, evolutionary computation and combinations of the two. The key features within Pearl include: modular and expandable components, opinionated module settings, Tensorboard integration, custom callbacks and comprehensive visualizations.

Thanos Konstantinidis, Giorgos Iacovides, Mingxue Xu et al.

There are multiple sources of financial news online which influence market movements and trader's decisions. This highlights the need for accurate sentiment analysis, in addition to having appropriate algorithmic trading techniques, to arrive at better informed trading decisions. Standard lexicon based sentiment approaches have demonstrated their power in aiding financial decisions. However, they are known to suffer from issues related to context sensitivity and word ordering. Large Language Models (LLMs) can also be used in this context, but they are not finance-specific and tend to require significant computational resources. To facilitate a finance specific LLM framework, we introduce a novel approach based on the Llama 2 7B foundational model, in order to benefit from its generative nature and comprehensive language manipulation. This is achieved by fine-tuning the Llama2 7B model on a small portion of supervised financial sentiment analysis data, so as to jointly handle the complexities of financial lexicon and context, and further equipping it with a neural network based decision mechanism. Such a generator-classifier scheme, referred to as FinLlama, is trained not only to classify the sentiment valence but also quantify its strength, thus offering traders a nuanced insight into financial news articles. Complementing this, the implementation of parameter-efficient fine-tuning through LoRA optimises trainable parameters, thus minimising computational and memory requirements, without sacrificing accuracy. Simulation results demonstrate the ability of the proposed FinLlama to provide a framework for enhanced portfolio management decisions and increased market returns. These results underpin the ability of FinLlama to construct high-return portfolios which exhibit enhanced resilience, even during volatile periods and unpredictable market events.

Andrea Cini, Alexander Jenkins, Danilo Mandic et al.

We address the problem of uncertainty quantification in time series forecasting by exploiting observations at correlated sequences. Relational deep learning methods leveraging graph representations are among the most effective tools for obtaining point estimates from spatiotemporal data and correlated time series. However, the problem of exploiting relational structures to estimate the uncertainty of such predictions has been largely overlooked in the same context. To this end, we propose a novel distribution-free approach based on the conformal prediction framework and quantile regression. Despite the recent applications of conformal prediction to sequential data, existing methods operate independently on each target time series and do not account for relationships among them when constructing the prediction interval. We fill this void by introducing a novel conformal prediction method based on graph deep learning operators. Our approach, named Conformal Relational Prediction (CoRel), does not require the relational structure (graph) to be known a priori and can be applied on top of any pre-trained predictor. Additionally, CoRel includes an adaptive component to handle non-exchangeable data and changes in the input time series. Our approach provides accurate coverage and achieves state-of-the-art uncertainty quantification in relevant benchmarks.

Giorgos Iacovides, Wuyang Zhou, Danilo Mandic

We propose a novel framework that leverages large language models (LLMs) to guide the rank selection in tensor network models for higher-order data analysis. By utilising the intrinsic reasoning capabilities and domain knowledge of LLMs, our approach offers enhanced interpretability of the rank choices and can effectively optimise the objective function. This framework enables users without specialised domain expertise to utilise tensor network decompositions and understand the underlying rationale within the rank selection process. Experimental results validate our method on financial higher-order datasets, demonstrating interpretable reasoning, strong generalisation to unseen test data, and its potential for self-enhancement over successive iterations. This work is placed at the intersection of large language models and higher-order data analysis.

Danilo Comminiello, Eleonora Grassucci, Danilo P. Mandic et al.

Hypercomplex algebras have recently been gaining prominence in the field of deep learning owing to the advantages of their division algebras over real vector spaces and their superior results when dealing with multidimensional signals in real-world 3D and 4D paradigms. This paper provides a foundational framework that serves as a roadmap for understanding why hypercomplex deep learning methods are so successful and how their potential can be exploited. Such a theoretical framework is described in terms of inductive bias, i.e., a collection of assumptions, properties, and constraints that are built into training algorithms to guide their learning process toward more efficient and accurate solutions. We show that it is possible to derive specific inductive biases in the hypercomplex domains, which extend complex numbers to encompass diverse numbers and data structures. These biases prove effective in managing the distinctive properties of these domains, as well as the complex structures of multidimensional and multimodal signals. This novel perspective for hypercomplex deep learning promises to both demystify this class of methods and clarify their potential, under a unifying framework, and in this way promotes hypercomplex models as viable alternatives to traditional real-valued deep learning for multidimensional signal processing.

Giorgos Iacovides, Wuyang Zhou, Danilo Mandic

Opinions expressed in online finance-related textual data are having an increasingly profound impact on trading decisions and market movements. This trend highlights the vital role of sentiment analysis as a tool for quantifying the nature and strength of such opinions. With the rapid development of Generative AI (GenAI), supervised fine-tuned (SFT) large language models (LLMs) have become the de facto standard for financial sentiment analysis. However, the SFT paradigm can lead to memorization of the training data and often fails to generalize to unseen samples. This is a critical limitation in financial domains, where models must adapt to previously unobserved events and the nuanced, domain-specific language of finance. To this end, we introduce FinDPO, the first finance-specific LLM framework based on post-training human preference alignment via Direct Preference Optimization (DPO). The proposed FinDPO achieves state-of-the-art performance on standard sentiment classification benchmarks, outperforming existing supervised fine-tuned models by 11% on the average. Uniquely, the FinDPO framework enables the integration of a fine-tuned causal LLM into realistic portfolio strategies through a novel 'logit-to-score' conversion, which transforms discrete sentiment predictions into continuous, rankable sentiment scores (probabilities). In this way, simulations demonstrate that FinDPO is the first sentiment-based approach to maintain substantial positive returns of 67% annually and strong risk-adjusted performance, as indicated by a Sharpe ratio of 2.0, even under realistic transaction costs of 5 basis points (bps).

Yuxuan Gu, Wuyang Zhou, Giorgos Iacovides et al.

The reasoning abilities of Large Language Models (LLMs) can be improved by structurally denoising their weights, yet existing techniques primarily focus on denoising the feed-forward network (FFN) of the transformer block, and can not efficiently utilise the Multi-head Attention (MHA) block, which is the core of transformer architectures. To address this issue, we propose a novel intuitive framework that, at its very core, performs MHA compression through a multi-head tensorisation process and the Tucker decomposition. This enables both higher-dimensional structured denoising and compression of the MHA weights, by enforcing a shared higher-dimensional subspace across the weights of the multiple attention heads. We demonstrate that this approach consistently enhances the reasoning capabilities of LLMs across multiple benchmark datasets, and for both encoder-only and decoder-only architectures, while achieving compression rates of up to $\sim 250$ times in the MHA weights, all without requiring any additional data, training, or fine-tuning. Furthermore, we show that the proposed method can be seamlessly combined with existing FFN-only-based denoising techniques to achieve further improvements in LLM reasoning performance.

Pauline Bourigault, Dongpo Xu, Danilo P. Mandic

We develop a robust quaternion recurrent neural network (QRNN) for real-time processing of 3D and 4D data with outliers. This is achieved by combining the real-time recurrent learning (RTRL) algorithm and the maximum correntropy criterion (MCC) as a loss function. While both the mean square error and maximum correntropy criterion are viable cost functions, it is shown that the non-quadratic maximum correntropy loss function is less sensitive to outliers, making it suitable for applications with multidimensional noisy or uncertain data. Both algorithms are derived based on the novel generalised HR (GHR) calculus, which allows for the differentiation of real functions of quaternion variables and offers the product and chain rules, thus enabling elegant and compact derivations. Simulation results in the context of motion prediction of chest internal markers for lung cancer radiotherapy, which includes regular and irregular breathing sequences, support the analysis.

Yuxuan Gu, Wuyang Zhou, Giorgos Iacovides et al.

Parameter-Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), have significantly reduced the number of trainable parameters needed in fine-tuning large language models (LLMs). Subsequent developments of LoRA-style adapters have diverged into two main directions: (1) enhancing model expressivity with high-rank adapters, and (2) pushing for further parameter reduction, as exemplified by vector-based methods. However, these approaches present a trade-off, as achieving the expressivity of high-rank weight updates typically comes at the cost of sacrificing the extreme parameter efficiency offered by vector-based techniques. To address this issue, we propose a vector-based random \underline{\textbf{Te}}nsor network for high-\underline{\textbf{R}}ank \underline{\textbf{A}}daptation (TeRA), a novel PEFT method that achieves high-rank weight updates while retaining the parameter efficiency of vector-based PEFT adapters. This is achieved by parameterizing the tensorized weight update matrix as a Tucker-like tensor network (TN), in which large randomly initialized factors are frozen and shared across layers, while only small layer-specific scaling vectors, formed by entries in diagonal factor matrices, are trained. This design effectively decouples the rank of the weight update matrix from the number of trainable parameters. Comprehensive experiments demonstrate that TeRA matches or even outperforms high-rank adapters, while requiring a trainable parameter count similar to vector-based methods. Theoretical analysis and ablation studies further validate the effectiveness of our approach.

Haozhe Tian, Qiyu Rao, Nina Moutonnet et al.

Matched filters are widely used to localise signal patterns due to their high efficiency and interpretability. However, their effectiveness deteriorates for low signal-to-noise ratio (SNR) signals, such as those recorded on edge devices, where prominent noise patterns can closely resemble the target within the limited length of the filter. One example is the ear-electrocardiogram (ear-ECG), where the cardiac signal is attenuated and heavily corrupted by artefacts. To address this, we propose the Sequential Matched Filter (SMF), a paradigm that replaces the conventional single matched filter with a sequence of filters designed by a Reinforcement Learning agent. By formulating filter design as a sequential decision-making process, SMF adaptively design signal-specific filter sequences that remain fully interpretable by revealing key patterns driving the decision-making. The proposed SMF framework has strong potential for reliable and interpretable clinical decision support, as demonstrated by its state-of-the-art R-peak detection and physiological state classification performance on two challenging real-world ECG datasets. The proposed formulation can also be extended to a broad range of applications that require accurate pattern localisation from noise-corrupted signals.

Wuyang Zhou, Giorgos Iacovides, Kriton Konstantinidis et al.

Tensor Network (TN) decompositions have emerged as an indispensable tool in Big Data analytics owing to their ability to provide compact low-rank representations, thus alleviating the ``Curse of Dimensionality'' inherent in handling higher-order data. At the heart of their success lies the concept of TN ranks, which governs the efficiency and expressivity of TN decompositions. However, unlike matrix ranks, TN ranks often lack a universal meaning and an intuitive interpretation, with their properties varying significantly across different TN structures. Consequently, TN ranks are frequently treated as empirically tuned hyperparameters, rather than as key design parameters inferred from domain knowledge. The aim of this Lecture Note is therefore to demystify the foundational yet frequently misunderstood concept of TN ranks through real-life examples and intuitive visualizations. We begin by illustrating how domain knowledge can guide the selection of TN ranks in widely-used models such as the Canonical Polyadic (CP) and Tucker decompositions. For more complex TN structures, we employ a self-explanatory graphical approach that generalizes to tensors of arbitrary order. Such a perspective naturally reveals the relationship between TN ranks and the corresponding ranks of tensor unfoldings (matrices), thereby circumventing cumbersome multi-index tensor algebra while facilitating domain-informed TN design. It is our hope that this Lecture Note will equip readers with a clear and unified understanding of the concept of TN rank, along with the necessary physical insight and intuition to support the selection, explainability, and deployment of tensor methods in both practical applications and educational contexts.

Mingxue Xu, Yao Lei Xu, Danilo P. Mandic

Small Language Models (SLMs, or on-device LMs) have significantly fewer parameters than Large Language Models (LLMs). They are typically deployed on low-end devices, like mobile phones and single-board computers. Unlike LLMs, which rely on increasing model size for better generalisation, SLMs designed for edge applications are expected to have adaptivity to the deployment environments and energy efficiency given the device battery life constraints, which are not addressed in datacenter-deployed LLMs. This paper addresses these two requirements by proposing a training-free token embedding compression approach using Tensor-Train Decomposition (TTD). Each pre-trained token embedding vector is converted into a lower-dimensional Matrix Product State (MPS). We comprehensively evaluate the extracted low-rank structures across compression ratio, language task performance, latency, and energy consumption on a typical low-end device, i.e. Raspberry Pi. Taking the sub-billion parameter versions of GPT-2/Cerebres-GPT and OPT models as examples, our approach achieves a comparable language task performance to the original model with around $2.0\times$ embedding layer compression, while the energy consumption of a single query drops by half.

Mingxue Xu, Lisa Alazraki, Danilo P. Mandic

Pruning assumes a subnetwork exists in the original deep neural network, which can achieve comparative model performance with less computation than the original. However, it is unclear how the model performance varies with the different subnetwork extractions. In this paper, we choose the representation dimension (or embedding dimension, model dimension, the dimension of the residual stream in the relevant literature) as the entry point to this issue. We investigate the linear transformations in the LLM transformer blocks and consider a specific structured pruning approach, SliceGPT, to extract the subnetworks of different representation dimensions. We mechanistically analyse the activation flow during the model forward passes, and find the representation dimension dominates the linear transformations, model predictions, and, finally, the model performance. Explicit analytical relations are given to calculate the pruned model performance (perplexity and accuracy) without actual evaluation, and are empirically validated with Llama-3-8B-Instruct and Phi-3-mini-4k-Instruct.

Alexander Jenkins, Andrea Cini, Joseph Barker et al.

Catheter ablation of Atrial Fibrillation (AF) consists of a one-size-fits-all treatment with limited success in persistent AF. This may be due to our inability to map the dynamics of AF with the limited resolution and coverage provided by sequential contact mapping catheters, preventing effective patient phenotyping for personalised, targeted ablation. Here we introduce FibMap, a graph recurrent neural network model that reconstructs global AF dynamics from sparse measurements. Trained and validated on 51 non-contact whole atria recordings, FibMap reconstructs whole atria dynamics from 10% surface coverage, achieving a 210% lower mean absolute error and an order of magnitude higher performance in tracking phase singularities compared to baseline methods. Clinical utility of FibMap is demonstrated on real-world contact mapping recordings, achieving reconstruction fidelity comparable to non-contact mapping. FibMap's state-spaces and patient-specific parameters offer insights for electrophenotyping AF. Integrating FibMap into clinical practice could enable personalised AF care and improve outcomes.

Harry J. Davies, Giorgos Iacovides, Danilo P. Mandic

The sheer scale of data required to train modern large language models (LLMs) poses significant risks, as models are likely to gain knowledge of sensitive topics such as bio-security, as well the ability to replicate copyrighted works. Methods designed to remove such knowledge must do so from all prompt directions, in a multi-lingual capacity and without degrading general model performance. To this end, we introduce the targeted angular reversal (TARS) method of knowledge removal from LLMs. The TARS method firstly leverages the LLM in combination with a detailed prompt to aggregate information about a selected concept in the internal representation space of the LLM. It then refines this approximate concept vector to trigger the concept token with high probability, by perturbing the approximate concept vector with noise and transforming it into token scores with the language model head. The feedforward weight vectors in the LLM which operate directly on the internal representation space, and have the highest cosine similarity with this targeting vector, are then replaced by a reversed targeting vector, thus limiting the ability of the concept to propagate through the model. The modularity of the TARS method allows for a sequential removal of concepts from Llama 3.1 8B, such as the famous literary detective Sherlock Holmes, and the planet Saturn. It is demonstrated that the probability of triggering target concepts can be reduced to 0.00 with as few as 1 TARS edit, whilst simultaneously removing the knowledge bi-directionally. Moreover, knowledge is shown to be removed across all languages despite only being targeted in English. Importantly, TARS has minimal impact on the general model capabilities, as after removing 5 diverse concepts in a modular fashion, there is minimal KL divergence in the next token probabilities of the LLM on large corpora of Wikipedia text (median of 0.0015).

Alexander Jenkins, Thiernithi Variddhisai, Ahmed El-Medany et al.

Graph Signal Processing (GSP) provides a powerful framework for analysing complex, interconnected systems by modelling data as signals on graphs. While recent advances have enabled graph topology learning from observed signals, existing methods often struggle with time-varying systems and real-time applications. To address this gap, we introduce AdaCGP, a sparsity-aware adaptive algorithm for dynamic graph topology estimation from multivariate time series. AdaCGP estimates the Graph Shift Operator (GSO) through recursive update formulae designed to address sparsity, shift-invariance, and bias. Through comprehensive simulations, we demonstrate that AdaCGP consistently outperforms multiple baselines across diverse graph topologies, achieving improvements exceeding 83% in GSO estimation compared to state-of-the-art methods while maintaining favourable computational scaling properties. Our variable splitting approach enables reliable identification of causal connections with near-zero false alarm rates and minimal missed edges. Applied to cardiac fibrillation recordings, AdaCGP tracks dynamic changes in propagation patterns more effectively than established methods like Granger causality, capturing temporal variations in graph topology that static approaches miss. The algorithm successfully identifies stability characteristics in conduction patterns that may maintain arrhythmias, demonstrating potential for clinical applications in diagnosis and treatment of complex biomedical systems.

Qingchen Wang, Zhe Li, Zdenka Babic et al.

A recent study on the interpretability of real-valued convolutional neural networks (CNNs) {Stankovic_Mandic_2023CNN} has revealed a direct and physically meaningful link with the task of finding features in data through matched filters. However, applying this paradigm to illuminate the interpretability of complex-valued CNNs meets a formidable obstacle: the extension of matched filtering to a general class of noncircular complex-valued data, referred to here as the widely linear matched filter (WLMF), has been only implicit in the literature. To this end, to establish the interpretability of the operation of complex-valued CNNs, we introduce a general WLMF paradigm, provide its solution and undertake analysis of its performance. For rigor, our WLMF solution is derived without imposing any assumption on the probability density of noise. The theoretical advantages of the WLMF over its standard strictly linear counterpart (SLMF) are provided in terms of their output signal-to-noise-ratios (SNRs), with WLMF consistently exhibiting enhanced SNR. Moreover, the lower bound on the SNR gain of WLMF is derived, together with condition to attain this bound. This serves to revisit the convolution-activation-pooling chain in complex-valued CNNs through the lens of matched filtering, which reveals the potential of WLMFs to provide physical interpretability and enhance explainability of general complex-valued CNNs. Simulations demonstrate the agreement between the theoretical and numerical results.

Andrea Cini, Danilo Mandic, Cesare Alippi

Relationships among time series can be exploited as inductive biases in learning effective forecasting models. In hierarchical time series, relationships among subsets of sequences induce hard constraints (hierarchical inductive biases) on the predicted values. In this paper, we propose a graph-based methodology to unify relational and hierarchical inductive biases in the context of deep learning for time series forecasting. In particular, we model both types of relationships as dependencies in a pyramidal graph structure, with each pyramidal layer corresponding to a level of the hierarchy. By exploiting modern - trainable - graph pooling operators we show that the hierarchical structure, if not available as a prior, can be learned directly from data, thus obtaining cluster assignments aligned with the forecasting objective. A differentiable reconciliation stage is incorporated into the processing architecture, allowing hierarchical constraints to act both as an architectural bias as well as a regularization element for predictions. Simulation results on representative datasets show that the proposed method compares favorably against the state of the art.

Yuyang Miao, Harry J. Davies, Danilo P. Mandic

Photoplethysmography (PPG) refers to the measurement of variations in blood volume using light and is a feature of most wearable devices. The PPG signals provide insight into the body's circulatory system and can be employed to extract various bio-features, such as heart rate and vascular ageing. Although several algorithms have been proposed for this purpose, many exhibit limitations, including heavy reliance on human calibration, high signal quality requirements, and a lack of generalisation. In this paper, we introduce a PPG signal processing framework that integrates graph theory and computer vision algorithms, to provide an analysis framework which is amplitude-independent and invariant to affine transformations. It also requires minimal preprocessing, fuses information through RGB channels and exhibits robust generalisation across tasks and datasets. The proposed VGTL-net achieves state-of-the-art performance in the prediction of vascular ageing and demonstrates robust estimation of continuous blood pressure waveforms.

Shuning Sun, Qiankun Diao, Dongpo Xu et al.

Convex optimization methods have been extensively used in the fields of communications and signal processing. However, the theory of quaternion optimization is currently not as fully developed and systematic as that of complex and real optimization. To this end, we establish an essential theory of convex quaternion optimization for signal processing based on the generalized Hamilton-real (GHR) calculus. This is achieved in a way which conforms with traditional complex and real optimization theory. For rigorous, We present five discriminant theorems for convex quaternion functions, and four discriminant criteria for strongly convex quaternion functions. Furthermore, we provide a fundamental theorem for the optimality of convex quaternion optimization problems, and demonstrate its utility through three applications in quaternion signal processing. These results provide a solid theoretical foundation for convex quaternion optimization and open avenues for further developments in signal processing applications.

Zehua Chen, Xu Tan, Ke Wang et al.

Denoising diffusion probabilistic models (diffusion models for short) require a large number of iterations in inference to achieve the generation quality that matches or surpasses the state-of-the-art generative models, which invariably results in slow inference speed. Previous approaches aim to optimize the choice of inference schedule over a few iterations to speed up inference. However, this results in reduced generation quality, mainly because the inference process is optimized separately, without jointly optimizing with the training process. In this paper, we propose InferGrad, a diffusion model for vocoder that incorporates inference process into training, to reduce the inference iterations while maintaining high generation quality. More specifically, during training, we generate data from random noise through a reverse process under inference schedules with a few iterations, and impose a loss to minimize the gap between the generated and ground-truth data samples. Then, unlike existing approaches, the training of InferGrad considers the inference process. The advantages of InferGrad are demonstrated through experiments on the LJSpeech dataset showing that InferGrad achieves better voice quality than the baseline WaveGrad under same conditions while maintaining the same voice quality as the baseline but with $3$x speedup ($2$ iterations for InferGrad vs $6$ iterations for WaveGrad).

Ljubisa Stankovic, Danilo Mandic

Deep Neural Networks (DNN) and especially Convolutional Neural Networks (CNN) are a de-facto standard for the analysis of large volumes of signals and images. Yet, their development and underlying principles have been largely performed in an ad-hoc and black box fashion. To help demystify CNNs, we revisit their operation from first principles and a matched filtering perspective. We establish that the convolution operation within CNNs, their very backbone, represents a matched filter which examines the input signal/image for the presence of pre-defined features. This perspective is shown to be physically meaningful, and serves as a basis for a step-by-step tutorial on the operation of CNNs, including pooling, zero padding, various ways of dimensionality reduction. Starting from first principles, both the feed-forward pass and the learning stage (via back-propagation) are illuminated in detail, both through a worked-out numerical example and the corresponding visualizations. It is our hope that this tutorial will help shed new light and physical intuition into the understanding and further development of deep neural networks.

Ljubisa Stankovic, Danilo Mandic

Graph Convolutional Neural Networks (GCNN) are becoming a preferred model for data processing on irregular domains, yet their analysis and principles of operation are rarely examined due to the black box nature of NNs. To this end, we revisit the operation of GCNNs and show that their convolution layers effectively perform matched filtering of input data with the chosen patterns (features). This allows us to provide a unifying account of GCNNs through a matched filter perspective, whereby the nonlinear ReLU and max-pooling layers are also discussed within the matched filtering framework. This is followed by a step-by-step guide on information propagation and learning in GCNNs. It is also shown that standard CNNs and fully connected NNs can be obtained as a special case of GCNNs. A carefully chosen numerical example guides the reader through the various steps of GCNN operation and learning both visually and numerically.

Bruno Scalzo Dees, Yao Lei Xu, Anthony G. Constantinides et al.

A unifying graph theoretic framework for the modelling of metro transportation networks is proposed. This is achieved by first introducing a basic graph framework for the modelling of the London underground system from a diffusion law point of view. This forms a basis for the analysis of both station importance and their vulnerability, whereby the concept of graph vertex centrality plays a key role. We next explore k-edge augmentation of a graph topology, and illustrate its usefulness both for improving the network robustness and as a planning tool. Upon establishing the graph theoretic attributes of the underlying graph topology, we proceed to introduce models for processing data on such a metro graph. Commuter movement is shown to obey the Fick's law of diffusion, where the graph Laplacian provides an analytical model for the diffusion process of commuter population dynamics. Finally, we also explore the application of modern deep learning models, such as graph neural networks and hyper-graph neural networks, as general purpose models for the modelling and forecasting of underground data, especially in the context of the morning and evening rush hours. Comprehensive simulations including the passenger in- and out-flows during the morning rush hour in London demonstrates the advantages of the graph models in metro planning and traffic management, a formal mathematical approach with wide economic implications.

Yao Lei Xu, Giuseppe G. Calvi, Danilo P. Mandic

Recurrent Neural Networks (RNNs) represent the de facto standard machine learning tool for sequence modelling, owing to their expressive power and memory. However, when dealing with large dimensional data, the corresponding exponential increase in the number of parameters imposes a computational bottleneck. The necessity to equip RNNs with the ability to deal with the curse of dimensionality, such as through the parameter compression ability inherent to tensors, has led to the development of the Tensor-Train RNN (TT-RNN). Despite achieving promising results in many applications, the full potential of the TT-RNN is yet to be explored in the context of interpretable financial modelling, a notoriously challenging task characterized by multi-modal data with low signal-to-noise ratio. To address this issue, we investigate the potential of TT-RNN in the task of financial forecasting of currencies. We show, through the analysis of TT-factors, that the physical meaning underlying tensor decomposition, enables the TT-RNN model to aid the interpretability of results, thus mitigating the notorious "black-box" issue associated with neural networks. Furthermore, simulation results highlight the regularization power of TT decomposition, demonstrating the superior performance of TT-RNN over its uncompressed RNN counterpart and other tensor forecasting methods.

Yao Lei Xu, Kriton Konstantinidis, Danilo P. Mandic

Modern data sources are typically of large scale and multi-modal natures, and acquired on irregular domains, which poses serious challenges to traditional deep learning models. These issues are partially mitigated by either extending existing deep learning algorithms to irregular domains through graphs, or by employing tensor methods to alleviate the computational bottlenecks imposed by the Curse of Dimensionality. To simultaneously resolve both these issues, we introduce a novel Multi-Graph Tensor Network (MGTN) framework, which leverages on the desirable properties of graphs, tensors and neural networks in a physically meaningful and compact manner. This equips MGTNs with the ability to exploit local information in irregular data sources at a drastically reduced parameter complexity, and over a range of learning paradigms such as regression, classification and reinforcement learning. The benefits of the MGTN framework, especially its ability to avoid overfitting through the inherent low-rank regularization properties of tensor networks, are demonstrated through its superior performance against competing models in the individual tensor, graph, and neural network domains.

Shengxi Li, Danilo Mandic

A large class of modern probabilistic learning systems assumes symmetric distributions, however, real-world data tend to obey skewed distributions and are thus not always adequately modelled through symmetric distributions. To address this issue, elliptical distributions are increasingly used to generalise symmetric distributions, and further improvements to skewed elliptical distributions have recently attracted much attention. However, existing approaches are either hard to estimate or have complicated and abstract representations. To this end, we propose to employ the von-Mises-Fisher (vMF) distribution to obtain an explicit and simple probability representation of the skewed elliptical distribution. This is shown not only to allow us to deal with non-symmetric learning systems, but also to provide a physically meaningful way of generalising skewed distributions. For rigour, our extension is proved to share important and desirable properties with its symmetric counterpart. We also demonstrate that the proposed vMF distribution is both easy to generate and stable to estimate, both theoretically and through examples.

Ljubisa Stankovic, Milos Brajovic, Danilo Mandic et al.

Within the Compressive Sensing (CS) paradigm, sparse signals can be reconstructed based on a reduced set of measurements. Reliability of the solution is determined by the uniqueness condition. With its mathematically tractable and feasible calculation, coherence index is one of very few CS metrics with a considerable practical importance. In this paper, we propose an improvement of the coherence based uniqueness relation for the matching pursuit algorithms. Starting from a simple and intuitive derivation of the standard uniqueness condition based on the coherence index, we derive a less conservative coherence index-based lower bound for signal sparsity. The results are generalized to the uniqueness condition of the $l_0$-norm minimization for a signal represented in two orthonormal bases.