Graph Neural Networks (GNNs) have achieved great success in representing data with dependencies by recursively propagating and aggregating messages along the edges. However, edges in real-world graphs often have varying degrees of difficulty, and some edges may even be noisy to the downstream tasks. Therefore, existing GNNs may lead to suboptimal learned representations because they usually treat every edge in the graph equally. On the other hand, Curriculum Learning (CL), which mimics the human learning principle of learning data samples in a meaningful order, has been shown to be effective in improving the generalization ability and robustness of representation learners by gradually proceeding from easy to more difficult samples during training. Unfortunately, existing CL strategies are designed for independent data samples and cannot trivially generalize to handle data dependencies. To address these issues, we propose a novel CL strategy to gradually incorporate more edges into training according to their difficulty from easy to hard, where the degree of difficulty is measured by how well the edges are expected given the model training status. We demonstrate the strength of our proposed method in improving the generalization ability and robustness of learned representations through extensive experiments on nine synthetic datasets and nine real-world datasets.

Abstract--Catastrophic forgetting (CF) poses a persistent challenge in continual learning (CL), especially within federated learning (FL) environments characterized by non-i.i.d. While existing research has largely focused on classification tasks in vision domains, the regression-based forecasting setting prevalent in IoT and edge applications remains underexplored. In this paper, we present the first benchmarking framework tailored to investigate CF in federated continual time series forecasting. Using the Beijing Multi-site Air Quality dataset across 12 decentralized clients, we systematically evaluate several CF mitigation strategies, including Replay, Elastic Weight Consolidation, Learning without Forgetting, and Synaptic Intelligence. Key contributions include: (i) introducing a new benchmark for CF in time series FL, (ii) conducting a comprehensive comparative analysis of state-of-the-art methods, and (iii) releasing a reproducible open-source framework. This work provides essential tools and insights for advancing continual learning in federated time-series forecasting systems. In recent years, federated learning (FL) has emerged as a powerful paradigm for distributed model training under strict data privacy constraints [1], [2]. Rather than transmitting raw data, FL enables edge devices (clients) to train models locally and share only model updates with a central server, which aggregates them into a global model.

Curriculum learning (CL) aims to improve training by presenting data from "easy" to "hard", yet defining and measuring linguistic difficulty remains an open challenge. We investigate whether human-curated simple language can serve as an effective signal for CL. Using the article-level labels from the Simple Wikipedia corpus, we compare label-based curricula to competence-based strategies relying on shallow heuristics. Our experiments with a BERT-tiny model show that adding simple data alone yields no clear benefit. However, structuring it via a curriculum -- especially when introduced first -- consistently improves perplexity, particularly on simple language. In contrast, competence-based curricula lead to no consistent gains over random ordering, probably because they fail to effectively separate the two classes. Our results suggest that human intuition about linguistic difficulty can guide CL for language model pre-training.

Manually designing (meta-)heuristics for the Vehicle Routing Problem (VRP) is a challenging task that requires significant domain expertise. Recently, data-driven approaches have emerged as a promising solution, automatically learning heuristics that perform well on training instances and generalize to unseen test cases. Such an approach learns (meta-)heuristics that can perform well on the training instances, expecting it to generalize well on the unseen test instances. A recent method, named GPGLS, uses Genetic Programming (GP) to learn the utility function in Guided Local Search (GLS) and solved large scale VRP effectively. However, the selection of appropriate training instances during the learning process remains an open question, with most existing studies including GPGLS relying on random instance selection. To address this, we propose a novel method, CL-GPGLS, which integrates Curriculum Learning (CL) into GPGLS. Our approach leverages a predefined curriculum to introduce training instances progressively, starting with simpler tasks and gradually increasing complexity, enabling the model to better adapt and optimize for large-scale VRP (LSVRP). Extensive experiments verify the effectiveness of CL-GPGLS, demonstrating significant performance improvements over three baseline methods.

Graph Neural Networks (GNNs) have achieved great success in representing data with dependencies by recursively propagating and aggregating messages along the edges. However, edges in real-world graphs often have varying degrees of difficulty, and some edges may even be noisy to the downstream tasks. Therefore, existing GNNs may lead to suboptimal learned representations because they usually treat every edge in the graph equally. On the other hand, Curriculum Learning (CL), which mimics the human learning principle of learning data samples in a meaningful order, has been shown to be effective in improving the generalization ability and robustness of representation learners by gradually proceeding from easy to more difficult samples during training. Unfortunately, existing CL strategies are designed for independent data samples and cannot trivially generalize to handle data dependencies. To address these issues, we propose a novel CL strategy to gradually incorporate more edges into training according to their difficulty from easy to hard, where the degree of difficulty is measured by how well the edges are expected given the model training status.

Curriculum Learning has been a popular strategy to improve the cognitive plausibility of Small-Scale Language Models (SSLMs) in the BabyLM Challenge. However, it has not led to considerable improvements over non-curriculum models. We assess whether theoretical linguistic acquisition theories can be used to specify more fine-grained curriculum learning strategies, creating age-ordered corpora of Child-Directed Speech for four typologically distant language families to implement SSLMs and acquisition-inspired curricula cross-lingually. Comparing the success of three objective curricula (Growing, Inwards and MMM) that precisely replicate the predictions of acquisition theories on a standard SSLM architecture, we find fine-grained acquisition-inspired curricula can outperform non-curriculum baselines and performance benefits of curricula strategies in SSLMs can be derived by specifying fine-grained language-specific curricula that precisely replicate language acquisition theories.

Continual Learning (CL) focuses on maximizing the predictive performance of a model across a non-stationary stream of data. Unfortunately, CL models tend to forget previous knowledge, thus often underperforming when compared with an offline model trained jointly on the entire data stream. Given that any CL model will eventually make mistakes, it is of crucial importance to build calibrated CL models: models that can reliably tell their confidence when making a prediction. Model calibration is an active research topic in machine learning, yet to be properly investigated in CL. We provide the first empirical study of the behavior of calibration approaches in CL, showing that CL strategies do not inherently learn calibrated models. To mitigate this issue, we design a continual calibration approach that improves the performance of post-processing calibration methods over a wide range of different benchmarks and CL strategies. CL does not necessarily need perfect predictive models, but rather it can benefit from reliable predictive models. We believe our study on continual calibration represents a first step towards this direction.

Deep Learning (DL) has made significant strides in various medical applications in recent years, achieving remarkable results. In the field of medical imaging, DL models can assist doctors in disease diagnosis by classifying pathologies in Chest X-ray images. However, training on new data to expand model capabilities and adapt to distribution shifts is a notable challenge these models face. Continual Learning (CL) has emerged as a solution to this challenge, enabling models to adapt to new data while retaining knowledge gained from previous experiences. Previous studies have analyzed the behavior of CL strategies in medical imaging regarding classification performance. However, when considering models that interact with sensitive information, such as in the medical domain, it is imperative to disaggregate the performance of socially salient groups. Indeed, DL algorithms can exhibit biases against certain sub-populations, leading to discrepancies in predictive performance across different groups identified by sensitive attributes such as age, race/ethnicity, sex/gender, and socioeconomic status. In this study, we go beyond the typical assessment of classification performance in CL and study bias evolution over successive tasks with domain-specific fairness metrics. Specifically, we evaluate the CL strategies using the well-known CheXpert (CXP) and ChestX-ray14 (NIH) datasets. We consider a class incremental scenario of five tasks with 12 pathologies. We evaluate the Replay, Learning without Forgetting (LwF), LwF Replay, and Pseudo-Label strategies. LwF and Pseudo-Label exhibit optimal classification performance, but when including fairness metrics in the evaluation, it is clear that Pseudo-Label is less biased. For this reason, this strategy should be preferred when considering real-world scenarios in which it is crucial to consider the fairness of the model.