Continual Learning (CL) is a highly relevant setting gaining traction in recent machine learning research. Among CL works, architectural and hybrid strategies are particularly effective due to their potential to adapt the model architecture as new tasks are presented. However, many existing solutions do not efficiently exploit model sparsity, and are prone to capacity saturation due to their inefficient use of available weights, which limits the number of learnable tasks. In this paper, we propose TinySubNets (TSN), a novel architectural CL strategy that addresses the issues through the unique combination of pruning with different sparsity levels, adaptive quantization, and weight sharing. Pruning identifies a subset of weights that preserve model performance, making less relevant weights available for future tasks. Adaptive quantization allows a single weight to be separated into multiple parts which can be assigned to different tasks. Weight sharing between tasks boosts the exploitation of capacity and task similarity, allowing for the identification of a better trade-off between model accuracy and capacity. These features allow TSN to efficiently leverage the available capacity, enhance knowledge transfer, and reduce computational resources consumption. Experimental results involving common benchmark CL datasets and scenarios show that our proposed strategy achieves better results in terms of accuracy than existing state-of-the-art CL strategies. Moreover, our strategy is shown to provide a significantly improved model capacity exploitation.

The recently proposed xLSTM is a powerful model that leverages expressive multiplicative gating and residual connections, providing the temporal capacity needed for long-horizon forecasting and representation learning. This architecture has demonstrated success in time series forecasting, lossless compression, and even large-scale language modeling tasks, where its linear memory footprint and fast inference make it a viable alternative to Transformers. Despite its growing popularity, no prior work has explored xLSTM for anomaly detection. In this work, we fill this gap by proposing xLSTMAD, the first anomaly detection method that integrates a full encoder-decoder xLSTM architecture, purpose-built for multivariate time series data. Our encoder processes input sequences to capture historical context, while the decoder is devised in two separate variants of the method. In the forecasting approach, the decoder iteratively generates forecasted future values xLSTMAD-F, while the reconstruction approach reconstructs the input time series from its encoded counterpart xLSTMAD-R. We investigate the performance of two loss functions: Mean Squared Error (MSE), and Soft Dynamic Time Warping (SoftDTW) to consider local reconstruction fidelity and global sequence alignment, respectively. We evaluate our method on the comprehensive TSB-AD-M benchmark, which spans 17 real-world datasets, using state-of-the-art challenging metrics such as VUS-PR. In our results, xLSTM showcases state-of-the-art accuracy, outperforming 23 popular anomaly detection baselines. Our paper is the first work revealing the powerful modeling capabilities of xLSTM for anomaly detection, paving the way for exciting new developments on this subject. Our code is available at: https://github.com/Nyderx/xlstmad.

Anomaly detection tools and methods present a key capability in modern cyberphysical and failure prediction systems. Despite the fast-paced development in deep learning architectures for anomaly detection, model optimization for a given dataset is a cumbersome and time-consuming process. Neuroevolution could be an effective and efficient solution to this problem, as a fully automated search method for learning optimal neural networks, supporting both gradient and nongradient fine-tuning. However, existing methods mostly focus on optimizing model architectures without taking into account feature subspaces and model weights. In this work, we propose anomaly detection neuroevolution (AD-NEv)-a scalable multilevel optimized neuroevolution framework for multivariate time-series anomaly detection. The method represents a novel approach to synergically: 1) optimize feature subspaces for an ensemble model based on the bagging technique; 2) optimize the model architecture of single anomaly detection models; and 3) perform nongradient fine-tuning of network weights. An extensive experimental evaluation on widely adopted multivariate anomaly detection benchmark datasets shows that the models extracted by AD-NEv outperform well-known deep learning architectures for anomaly detection. Moreover, results show that AD-NEv can perform the whole process efficiently, presenting high scalability when multiple graphics processing units (GPUs) are available.

Efficient flight scheduling is crucial to properly allocate airline resources, but even the best flight schedule has to face unexpected delays and disruptions. The ability to recover from such disruptions is essential for airlines to minimize the negative impact on their revenue and reputation. In this context, machine learning-based methods can be used to identify suitable recovery methods as unexpected events occur. Reinforcement learning approaches are especially promising since they extract suitable solutions much more efficiently than conventional optimization and meta-heuristics methods and provide timely rescheduling capabilities for airlines, which translates into reduced capital and reputation losses. However, current works either do not leverage deep learning or focus on simple scenarios that do not fully entail real-world complexities, resulting in limited efficiency or sub-optimal solutions. In this paper, we propose an ensemble of two deep learning approaches: Deep Double Q-Learning (DDQL) and Advantage Actor-Critic (A2C). The models aim to minimize the total delays caused by disruptions by swapping aircraft and delaying flights as recovery options. We perform experiments with a benchmark dataset and a real-world airline dataset, showing that our method is effective in providing a significant reduction of delays caused by disruptions.

Low Autocorrelation Binary Sequence (LABS) remains an open complex optimization problem with multiple applications.Existing studies rely primarily on advanced solvers based on local search heuristics, such as the steepest-descent local search algorithm (SDLS), Tabu search, or xLastovka algorithms.These approaches require searching through a large solution space, which is a computationally heavy and time-consuming process, leading to slower convergence.To improve convergence speed and allow for finding better solutions within a limited time, we propose the Deep Double Q-learning reinforcement learning algorithm for the LABS problem to support heuristic methods.The model aims to narrow down the search space without causing a drop in the final efficiency.Our experimental study showcases that the proposed approach is a promising direction for developing a highly efficient method for the LABS problem.* {dzurek, pietron, kpietak, kfaber}

Abstract Continual learning (CL) is one of the most promising trends in recent machine learning research. Its goal is to go beyond classical assumptions in machine learning and develop models and learning strategies that present high robustness in dynamic environments. This goal is realized by designing strategies that simultaneously foster the incorporation of new knowledge while avoiding forgetting past knowledge. The landscape of CL research is fragmented into several learning evaluation protocols, comprising different learning tasks, datasets, and evaluation metrics. Additionally, the benchmarks adopted so far are still distant from the complexity of real-world scenarios, and are usually tailored to highlight capabilities specific to certain strategies. In such a landscape, it is hard to clearly and objectively assess models and strategies. In this work, we fill this gap for CL on image data by introducing two novel CL benchmarks that involve multiple heterogeneous tasks from six image datasets, with varying levels of complexity and quality. Our aim is to fairly evaluate current state-of-the-art CL strategies on a common ground that is closer to complex real-world scenarios. We additionally structure our benchmarks so that tasks are presented in increasing and decreasing order of complexity—according to a curriculum—in order to evaluate if current CL models are able to exploit structure across tasks. We devote particular emphasis to providing the CL community with a rigorous and reproducible evaluation protocol for measuring the ability of a model to generalize and not to forget while learning. Furthermore, we provide an extensive experimental evaluation showing that popular CL strategies, when challenged with our proposed benchmarks, yield sub-par performance, high levels of forgetting, and present a limited ability to effectively leverage curriculum task ordering. We believe that these results highlight the need for rigorous comparisons in future CL works as well as pave the way to design new CL strategies that are able to deal with more complex scenarios.

Continual learning (CL) is a challenging machine learning setting that is attracting the interest of an increasing number of researchers. Among recent CL works, architectural strategies appear particularly promising due to their potential to expand and adapt the model architecture as new tasks are presented. However, existing solutions do not efficiently exploit model sparsity due to the adoption of constant pruning ratios. Moreover, current approaches exhibit a tendency to quickly saturate model capacity since the number of weights is limited and each weight is restricted to a single value. In this paper, we propose Ada-QPacknet, a novel architectural CL method that resorts to adaptive pruning and quantization. These two features allow our model to overcome the two crucial issues of effective exploitation of model sparsity and efficient use of model capacity. Specifically, adaptive pruning restores model capacity by reducing the number of weights assigned to each task to a smaller subset of weights that preserves the performance of the full set, allowing other weights to be used for future tasks. Adaptive quantization separates each weight into multiple components with adaptively reduced bit-width, allowing a single weight to solve more than one task without significant performance drops, leading to improved exploitation of model capacity. Experimental results on benchmark CL scenarios show that our proposed method achieves better results in terms of accuracy than existing rehearsal, regularization, and architectural CL strategies. Moreover, our method significantly outperforms forget-free competitors in terms of efficient exploitation of model capacity.

Lifelong learning is becoming a popular trend in modern machine learning research. Domain-incremental scenarios are particularly relevant since they closely reflects real-world characteristics. However, one open challenge is the ability to devise scenarios that entail the inherent unpredictability and complexities of domains still unexplored in lifelong learning. To tackle this issue, we propose a framework for domain-incremental scenario generation. The framework enables users to create lifelong learning scenarios using any image dataset, and leveraging a fully customizable pool of transformation functions. We devise an algorithm and criteria that iteratively guide users in evaluating the inclusion of candidate transformation functions to the scenario and in making this decision based on desired outcomes. Experimental results with common lifelong learning strategies and benchmark datasets show that our framework is highly flexible since it allows tweaking complexities and challenges incorporated in generated scenarios. Furthermore, experimental results show that there is a gap between state-of-the-art learning strategies and a proposed upper bound to be exploited in the design of future learning strategies.

The following paper presents a simple and fast liveness detection method based on gaze direction estimation under a challenge-response user authentication scenario.To estimate a line of sight, a procedure composed of several steps, including face and eye detection, derivation of gaze direction representation and subsequent classification, has been proposed.The proposed, novel gaze orientation descriptor is easy to compute and it provides sufficiently accurate estimates for the considered task.To assess a probability of genuine biometric trait presentation, recorded gaze direction responses induced by presentation of a randomly generated on-screen object, are matched against expected patterns.