Machine Learning (cs.LG)

Abstract: Improving performance in multiple domains is a challenging task, and often requires significant amounts of data to train and test models. Active learning techniques provide a promising solution by enabling models to select the most informative samples for labeling, thus reducing the amount of labeled data required to achieve high performance. In this paper, we present an active learning-based framework for improving performance across multiple domains. Our approach consists of two stages: first, we use an initial set of labeled data to train a base model, and then we iteratively select the most informative samples for labeling to refine the model. We evaluate our approach on several multi-domain datasets, including image classification, sentiment analysis, and object recognition. Our experiments demonstrate that our approach consistently outperforms baseline methods and achieves state-of-the-art performance on several datasets. We also show that our method is highly efficient, requiring significantly fewer labeled samples than other active learning-based methods. Overall, our approach provides a practical and effective solution for improving performance across multiple domains using active learning techniques.

Abstract: Multi-Agent Reinforcement Learning (MARL) discovers policies that maximize reward but do not have safety guarantees during the learning and deployment phases. Although shielding with Linear Temporal Logic (LTL) is a promising formal method to ensure safety in single-agent Reinforcement Learning (RL), it results in conservative behaviors when scaling to multi-agent scenarios. Additionally, it poses computational challenges for synthesizing shields in complex multi-agent environments. This work introduces Model-based Dynamic Shielding (MBDS) to support MARL algorithm design. Our algorithm synthesizes distributive shields, which are reactive systems running in parallel with each MARL agent, to monitor and rectify unsafe behaviors. The shields can dynamically split, merge, and recompute based on agents' states. This design enables efficient synthesis of shields to monitor agents in complex environments without coordination overheads. We also propose an algorithm to synthesize shields without prior knowledge of the dynamics model. The proposed algorithm obtains an approximate world model by interacting with the environment during the early stage of exploration, making our MBDS enjoy formal safety guarantees with high probability. We demonstrate in simulations that our framework can surpass existing baselines in terms of safety guarantees and learning performance.

Abstract: Labeling mistakes are frequently encountered in real-world applications. If not treated well, the labeling mistakes can deteriorate the classification performances of a model seriously. To address this issue, we propose an improved Naive Bayes method for text classification. It is analytically simple and free of subjective judgements on the correct and incorrect labels. By specifying the generating mechanism of incorrect labels, we optimize the corresponding log-likelihood function iteratively by using an EM algorithm. Our simulation and experiment results show that the improved Naive Bayes method greatly improves the performances of the Naive Bayes method with mislabeled data.

Abstract: Soft-sensors are gaining popularity due to their ability to provide estimates of key process variables with little intervention required on the asset and at a low cost. In oil and gas production, virtual flow metering (VFM) is a popular soft-sensor that attempts to estimate multiphase flow rates in real time. VFMs are based on models, and these models require calibration. The calibration is highly dependent on the application, both due to the great diversity of the models, and in the available measurements. The most accurate calibration is achieved by careful tuning of the VFM parameters to well tests, but this can be work intensive, and not all wells have frequent well test data available. This paper presents a calibration method based on the measurement provided by the production separator, and the assumption that the observed flow should be equal to the sum of flow rates from each individual well. This allows us to jointly calibrate the VFMs continuously. The method applies Sequential Monte Carlo (SMC) to infer a tuning factor and the flow composition for each well. The method is tested on a case with ten wells, using both synthetic and real data. The results are promising and the method is able to provide reasonable estimates of the parameters without relying on well tests. However, some challenges are identified and discussed, particularly related to the process noise and how to manage varying data quality.

Abstract: When choosing between competing symbolic models for a data set, a human will naturally prefer the "simpler" expression or the one which more closely resembles equations previously seen in a similar context. This suggests a non-uniform prior on functions, which is, however, rarely considered within a symbolic regression (SR) framework. In this paper we develop methods to incorporate detailed prior information on both functions and their parameters into SR. Our prior on the structure of a function is based on a $n$-gram language model, which is sensitive to the arrangement of operators relative to one another in addition to the frequency of occurrence of each operator. We also develop a formalism based on the Fractional Bayes Factor to treat numerical parameter priors in such a way that models may be fairly compared though the Bayesian evidence, and explicitly compare Bayesian, Minimum Description Length and heuristic methods for model selection. We demonstrate the performance of our priors relative to literature standards on benchmarks and a real-world dataset from the field of cosmology.

Abstract: Falls are the public health issue for the elderly all over the world since the fall-induced injuries are associated with a large amount of healthcare cost. Falls can cause serious injuries, even leading to death if the elderly suffers a "long-lie". Hence, a reliable fall detection (FD) system is required to provide an emergency alarm for first aid. Due to the advances in wearable device technology and artificial intelligence, some fall detection systems have been developed using machine learning and deep learning methods to analyze the signal collected from accelerometer and gyroscopes. In order to achieve better fall detection performance, an ensemble model that combines a coarse-fine convolutional neural network and gated recurrent unit is proposed in this study. The parallel structure design used in this model restores the different grains of spatial characteristics and capture temporal dependencies for feature representation. This study applies the FallAllD public dataset to validate the reliability of the proposed model, which achieves a recall, precision, and F-score of 92.54%, 96.13%, and 94.26%, respectively. The results demonstrate the reliability of the proposed ensemble model in discriminating falls from daily living activities and its superior performance compared to the state-of-the-art convolutional neural network long short-term memory (CNN-LSTM) for FD.

Abstract: Heterogeneous graph neural networks aim to discover discriminative node embeddings and relations from multi-relational networks.One challenge of heterogeneous graph learning is the design of learnable meta-paths, which significantly influences the quality of learned embeddings.Thus, in this paper, we propose an Attributed Multi-Order Graph Convolutional Network (AMOGCN), which automatically studies meta-paths containing multi-hop neighbors from an adaptive aggregation of multi-order adjacency matrices. The proposed model first builds different orders of adjacency matrices from manually designed node connections. After that, an intact multi-order adjacency matrix is attached from the automatic fusion of various orders of adjacency matrices. This process is supervised by the node semantic information, which is extracted from the node homophily evaluated by attributes. Eventually, we utilize a one-layer simplifying graph convolutional network with the learned multi-order adjacency matrix, which is equivalent to the cross-hop node information propagation with multi-layer graph neural networks. Substantial experiments reveal that AMOGCN gains superior semi-supervised classification performance compared with state-of-the-art competitors.

Abstract: This paper proposes a framework for developing forecasting models by streamlining the connections between core components of the developmental process. The proposed framework enables swift and robust integration of new datasets, experimentation on different algorithms, and selection of the best models. We start with the datasets of different issues and apply pre-processing steps to clean and engineer meaningful representations of time-series data. To identify robust training configurations, we introduce a novel mechanism of multiple cross-validation strategies. We apply different evaluation metrics to find the best-suited models for varying applications. One of the referent applications is our participation in the intelligent forecasting competition held by the United States Agency of International Development (USAID). Finally, we leverage the flexibility of the framework by applying different evaluation metrics to assess the performance of the models in inventory management settings.

Abstract: Effective quantification of uncertainty is an essential and still missing step towards a greater adoption of deep-learning approaches in different applications, including mission-critical ones. In particular, investigations on the predictive uncertainty of deep-learning models describing non-linear dynamical systems are very limited to date. This paper is aimed at filling this gap and presents preliminary results on uncertainty quantification for system identification with neural state-space models. We frame the learning problem in a Bayesian probabilistic setting and obtain posterior distributions for the neural network's weights and outputs through approximate inference techniques. Based on the posterior, we construct credible intervals on the outputs and define a surprise index which can effectively diagnose usage of the model in a potentially dangerous out-of-distribution regime, where predictions cannot be trusted.

Abstract: Sepsis is a life-threatening organ malfunction caused by the host's inability to fight infection, which can lead to death without proper and immediate treatment. Therefore, early diagnosis and medical treatment of sepsis in critically ill populations at high risk for sepsis and sepsis-associated mortality are vital to providing the patient with rapid therapy. Studies show that advancing sepsis detection by 6 hours leads to earlier administration of antibiotics, which is associated with improved mortality. However, clinical scores like Sequential Organ Failure Assessment (SOFA) are not applicable for early prediction, while machine learning algorithms can help capture the progressing pattern for early prediction. Therefore, we aim to develop a machine learning algorithm that predicts sepsis onset 6 hours before it is suspected clinically. Although some machine learning algorithms have been applied to sepsis prediction, many of them did not consider the fact that six hours is not a small gap. To overcome this big gap challenge, we explore a multi-subset approach in which the likelihood of sepsis occurring earlier than 6 hours is output from a previous subset and feed to the target subset as additional features. Moreover, we use the hourly sampled data like vital signs in an observation window to derive a temporal change trend to further assist, which however is often ignored by previous studies. Our empirical study shows that both the multi-subset approach to alleviating the 6-hour gap and the added temporal trend features can help improve the performance of sepsis-related early prediction.

Abstract: This paper introduces a comprehensive, multi-stage machine learning methodology that effectively integrates information systems and artificial intelligence to enhance decision-making processes within the domain of operations research. The proposed framework adeptly addresses common limitations of existing solutions, such as the neglect of data-driven estimation for vital production parameters, exclusive generation of point forecasts without considering model uncertainty, and lacking explanations regarding the sources of such uncertainty. Our approach employs Quantile Regression Forests for generating interval predictions, alongside both local and global variants of SHapley Additive Explanations for the examined predictive process monitoring problem. The practical applicability of the proposed methodology is substantiated through a real-world production planning case study, emphasizing the potential of prescriptive analytics in refining decision-making procedures. This paper accentuates the imperative of addressing these challenges to fully harness the extensive and rich data resources accessible for well-informed decision-making.

Abstract: This paper presents a systematic investigation into the effectiveness of Self-Supervised Learning (SSL) methods for Electrocardiogram (ECG) arrhythmia detection. We begin by conducting a novel distribution analysis on three popular ECG-based arrhythmia datasets: PTB-XL, Chapman, and Ribeiro. To the best of our knowledge, our study is the first to quantify these distributions in this area. We then perform a comprehensive set of experiments using different augmentations and parameters to evaluate the effectiveness of various SSL methods, namely SimCRL, BYOL, and SwAV, for ECG representation learning, where we observe the best performance achieved by SwAV. Furthermore, our analysis shows that SSL methods achieve highly competitive results to those achieved by supervised state-of-the-art methods. To further assess the performance of these methods on both In-Distribution (ID) and Out-of-Distribution (OOD) ECG data, we conduct cross-dataset training and testing experiments. Our comprehensive experiments show almost identical results when comparing ID and OOD schemes, indicating that SSL techniques can learn highly effective representations that generalize well across different OOD datasets. This finding can have major implications for ECG-based arrhythmia detection. Lastly, to further analyze our results, we perform detailed per-disease studies on the performance of the SSL methods on the three datasets.

Abstract: Unmanned aerial vehicles (UAV) or drones play many roles in a modern smart city such as the delivery of goods, mapping real-time road traffic and monitoring pollution. The ability of drones to perform these functions often requires the support of machine learning technology. However, traditional machine learning models for drones encounter data privacy problems, communication costs and energy limitations. Federated Learning, an emerging distributed machine learning approach, is an excellent solution to address these issues. Federated learning (FL) allows drones to train local models without transmitting raw data. However, existing FL requires a central server to aggregate the trained model parameters of the UAV. A failure of the central server can significantly impact the overall training. In this paper, we propose two aggregation methods: Commutative FL and Alternate FL, based on the existing architecture of decentralised Federated Learning for UAV Networks (DFL-UN) by adding a unique aggregation method of decentralised FL. Those two methods can effectively control energy consumption and communication cost by controlling the number of local training epochs, local communication, and global communication. The simulation results of the proposed training methods are also presented to verify the feasibility and efficiency of the architecture compared with two benchmark methods (e.g. standard machine learning training and standard single aggregation server training). The simulation results show that the proposed methods outperform the benchmark methods in terms of operational stability, energy consumption and communication cost.

Abstract: Deep reinforcement learning (DRL) has demonstrated its potential in solving complex manufacturing decision-making problems, especially in a context where the system learns over time with actual operation in the absence of training data. One interesting and challenging application for such methods is the assembly sequence planning (ASP) problem. In this paper, we propose an approach to the implementation of DRL methods in ASP. The proposed approach introduces in the RL environment parametric actions to improve training time and sample efficiency and uses two different reward signals: (1) user's preferences and (2) total assembly time duration. The user's preferences signal addresses the difficulties and non-ergonomic properties of the assembly faced by the human and the total assembly time signal enforces the optimization of the assembly. Three of the most powerful deep RL methods were studied, Advantage Actor-Critic (A2C), Deep Q-Learning (DQN), and Rainbow, in two different scenarios: a stochastic and a deterministic one. Finally, the performance of the DRL algorithms was compared to tabular Q-Learnings performance. After 10,000 episodes, the system achieved near optimal behaviour for the algorithms tabular Q-Learning, A2C, and Rainbow. Though, for more complex scenarios, the algorithm tabular Q-Learning is expected to underperform in comparison to the other 2 algorithms. The results support the potential for the application of deep reinforcement learning in assembly sequence planning problems with human interaction.

Abstract: Adversarial examples have been found for various deep as well as shallow learning models, and have at various times been suggested to be either fixable model-specific bugs, or else inherent dataset feature, or both. We present theoretical and empirical results to show that adversarial examples are approximate discontinuities resulting from models that specify approximately bijective maps $f: \Bbb R^n \to \Bbb R^m; n \neq m$ over their inputs, and this discontinuity follows from the topological invariance of dimension.

Abstract: Machine learning algorithms play an important role in a variety of important decision-making processes, including targeted advertisement displays, home loan approvals, and criminal behavior predictions. Given the far-reaching impact of these algorithms, it is crucial that they operate fairly, free from bias or prejudice towards certain groups in the population. Ensuring impartiality in these algorithms is essential for promoting equality and avoiding discrimination. To this end we introduce a unified framework for randomized subset selection that incorporates group fairness constraints. Our problem involves a global utility function and a set of group utility functions for each group, here a group refers to a group of individuals (e.g., people) sharing the same attributes (e.g., gender). Our aim is to generate a distribution across feasible subsets, specifying the selection probability of each feasible set, to maximize the global utility function while meeting a predetermined quota for each group utility function in expectation. Note that there may not necessarily be any direct connections between the global utility function and each group utility function. We demonstrate that this framework unifies and generalizes many significant applications in machine learning and operations research. Our algorithmic results either improves the best known result or provide the first approximation algorithms for new applications.

Abstract: Recent works have shown that large models pretrained on common visual learning tasks can provide useful representations for a wide range of specialized perception problems, as well as a variety of robotic manipulation tasks. While prior work on robotic manipulation has predominantly used frozen pretrained features, we demonstrate that in robotics this approach can fail to reach optimal performance, and that fine-tuning of the full model can lead to significantly better results. Unfortunately, fine-tuning disrupts the pretrained visual representation, and causes representational drift towards the fine-tuned task thus leading to a loss of the versatility of the original model. We introduce "lossless adaptation" to address this shortcoming of classical fine-tuning. We demonstrate that appropriate placement of our parameter efficient adapters can significantly reduce the performance gap between frozen pretrained representations and full end-to-end fine-tuning without changes to the original representation and thus preserving original capabilities of the pretrained model. We perform a comprehensive investigation across three major model architectures (ViTs, NFNets, and ResNets), supervised (ImageNet-1K classification) and self-supervised pretrained weights (CLIP, BYOL, Visual MAE) in 3 task domains and 35 individual tasks, and demonstrate that our claims are strongly validated in various settings.

Abstract: Without access to the source data, source-free domain adaptation (SFDA) transfers knowledge from a source-domain trained model to target domains. Recently, SFDA has gained popularity due to the need to protect the data privacy of the source domain, but it suffers from catastrophic forgetting on the source domain due to the lack of data. To systematically investigate the mechanism of catastrophic forgetting, we first reimplement previous SFDA approaches within a unified framework and evaluate them on four benchmarks. We observe that there is a trade-off between adaptation gain and forgetting loss, which motivates us to design a consistency regularization to mitigate forgetting. In particular, we propose a continual source-free domain adaptation approach named CoSDA, which employs a dual-speed optimized teacher-student model pair and is equipped with consistency learning capability. Our experiments demonstrate that CoSDA outperforms state-of-the-art approaches in continuous adaptation. Notably, our CoSDA can also be integrated with other SFDA methods to alleviate forgetting.

Abstract: The remarkable performance of overparameterized deep neural networks (DNNs) must arise from an interplay between network architecture, training algorithms, and structure in the data. To disentangle these three components, we apply a Bayesian picture, based on the functions expressed by a DNN, to supervised learning. The prior over functions is determined by the network, and is varied by exploiting a transition between ordered and chaotic regimes. For Boolean function classification, we approximate the likelihood using the error spectrum of functions on data. When combined with the prior, this accurately predicts the posterior, measured for DNNs trained with stochastic gradient descent. This analysis reveals that structured data, combined with an intrinsic Occam's razor-like inductive bias towards (Kolmogorov) simple functions that is strong enough to counteract the exponential growth of the number of functions with complexity, is a key to the success of DNNs.

Abstract: Multi-objective portfolio optimisation is a critical problem researched across various fields of study as it achieves the objective of maximising the expected return while minimising the risk of a given portfolio at the same time. However, many studies fail to include realistic constraints in the model, which limits practical trading strategies. This study introduces realistic constraints, such as transaction and holding costs, into an optimisation model. Due to the non-convex nature of this problem, metaheuristic algorithms, such as NSGA-II, R-NSGA-II, NSGA-III and U-NSGA-III, will play a vital role in solving the problem. Furthermore, a learnheuristic approach is taken as surrogate models enhance the metaheuristics employed. These algorithms are then compared to the baseline metaheuristic algorithms, which solve a constrained, multi-objective optimisation problem without using learnheuristics. The results of this study show that, despite taking significantly longer to run to completion, the learnheuristic algorithms outperform the baseline algorithms in terms of hypervolume and rate of convergence. Furthermore, the backtesting results indicate that utilising learnheuristics to generate weights for asset allocation leads to a lower risk percentage, higher expected return and higher Sharpe ratio than backtesting without using learnheuristics. This leads us to conclude that using learnheuristics to solve a constrained, multi-objective portfolio optimisation problem produces superior and preferable results than solving the problem without using learnheuristics.

Abstract: We consider an important problem in scientific discovery, identifying sparse governing equations for nonlinear dynamical systems. This involves solving sparse ridge regression problems to provable optimality in order to determine which terms drive the underlying dynamics. We propose a fast algorithm, OKRidge, for sparse ridge regression, using a novel lower bound calculation involving, first, a saddle point formulation, and from there, either solving (i) a linear system or (ii) using an ADMM-based approach, where the proximal operators can be efficiently evaluated by solving another linear system and an isotonic regression problem. We also propose a method to warm-start our solver, which leverages a beam search. Experimentally, our methods attain provable optimality with run times that are orders of magnitude faster than those of the existing MIP formulations solved by the commercial solver Gurobi.

Abstract: We propose a novel way of solving the issue of classification of out-of-vocabulary gestures using Artificial Neural Networks (ANNs) trained in the Generative Adversarial Network (GAN) framework. A generative model augments the data set in an online fashion with new samples and stochastic target vectors, while a discriminative model determines the class of the samples. The approach was evaluated on the UC2017 SG and UC2018 DualMyo data sets. The generative models performance was measured with a distance metric between generated and real samples. The discriminative models were evaluated by their accuracy on trained and novel classes. In terms of sample generation quality, the GAN is significantly better than a random distribution (noise) in mean distance, for all classes. In the classification tests, the baseline neural network was not capable of identifying untrained gestures. When the proposed methodology was implemented, we found that there is a trade-off between the detection of trained and untrained gestures, with some trained samples being mistaken as novelty. Nevertheless, a novelty detection accuracy of 95.4% or 90.2% (depending on the data set) was achieved with just 5% loss of accuracy on trained classes.

Abstract: Individual human decision-makers may benefit from different forms of support to improve decision outcomes. However, a key question is which form of support will lead to accurate decisions at a low cost. In this work, we propose learning a decision support policy that, for a given input, chooses which form of support, if any, to provide. We consider decision-makers for whom we have no prior information and formalize learning their respective policies as a multi-objective optimization problem that trades off accuracy and cost. Using techniques from stochastic contextual bandits, we propose $\texttt{THREAD}$, an online algorithm to personalize a decision support policy for each decision-maker, and devise a hyper-parameter tuning strategy to identify a cost-performance trade-off using simulated human behavior. We provide computational experiments to demonstrate the benefits of $\texttt{THREAD}$ compared to offline baselines. We then introduce $\texttt{Modiste}$, an interactive tool that provides $\texttt{THREAD}$ with an interface. We conduct human subject experiments to show how $\texttt{Modiste}$ learns policies personalized to each decision-maker and discuss the nuances of learning decision support policies online for real users.

Abstract: Interpretability methods are valuable only if their explanations faithfully describe the explained model. In this work, we consider neural networks whose predictions are invariant under a specific symmetry group. This includes popular architectures, ranging from convolutional to graph neural networks. Any explanation that faithfully explains this type of model needs to be in agreement with this invariance property. We formalize this intuition through the notion of explanation invariance and equivariance by leveraging the formalism from geometric deep learning. Through this rigorous formalism, we derive (1) two metrics to measure the robustness of any interpretability method with respect to the model symmetry group; (2) theoretical robustness guarantees for some popular interpretability methods and (3) a systematic approach to increase the invariance of any interpretability method with respect to a symmetry group. By empirically measuring our metrics for explanations of models associated with various modalities and symmetry groups, we derive a set of 5 guidelines to allow users and developers of interpretability methods to produce robust explanations.