In many domains, including healthcare, biology, and climate science, time series are irregularly sampled with variable time between successive observations and different subsets of variables (sensors) are observed at different time points, even after alignment to start events. These data create multiple challenges for prevailing models that assume fully observed and fixed-length feature representations. To address these challenges, it is essential to understand the relationships between sensors and how they evolve over time. It considers both inter-sensor relationships shared across samples and those unique to each sample that can vary with time, and it adaptively estimates misaligned observations based on nearby observations. Multivariate time series are prevalent in a variety of domains including healthcare, space science, cybersecurity, biology, and finance (Ravuri et al., 2021; Sousa et al., 2020; Sezer et al., 2020; Fawaz et al., 2019; Abanda et al., 2019; Tang et al., 2018). Practical issues often exist in collecting sensor measurements that lead to various types of irregularities caused by missing observations, such as cost saving, sensor failures, external forces in physical scenarios, medical interventions, to name a few (Choi et al., 2020). While temporal machine learning models usually assume fully observable and fixed-size input data, irregularly sampled time series raise considerable challenges. For example, the observations of multiple sensors are not well-aligned; the time intervals among adjacent observations are different across sensors; and different samples have different numbers of observations for different subsets of sensors recorded at different time points.

Label smoothing is widely used in deep neural networks for multi-class classification. While it enhances model generalization and reduces overconfidence by aiming to lower the probability for the predicted class, it distorts the predicted probabilities of other classes resulting in poor class-wise calibration. Another method for enhancing model generalization is self-distillation where the predictions of a teacher network trained with one-hot labels are used as the target for training a student network. We take inspiration from both label smoothing and self-distillation and propose two novel instance-based label smoothing approaches, where a teacher network trained with hard one-hot labels is used to determine the amount of per class smoothness applied to each instance. The assigned smoothing factor is non-uniformly distributed along with the classes according to their similarity with the actual class. Our methods show better generalization and calibration over standard label smoothing on various deep neural architectures and image classification datasets.

Continual learning agents should incrementally learn a sequence of tasks while satisfying two main desiderata: accumulating on previous knowledge without forgetting and transferring previous relevant knowledge to help in future learning. Existing research largely focuses on alleviating the catastrophic forgetting problem. There, an agent is altered to prevent forgetting based solely on previous tasks. This hinders the balance between preventing forgetting and maximizing the forward transfer. In response to this, we investigate the stability-plasticity dilemma to determine which model components are eligible to be reused, added, fixed, or updated to achieve this balance. We address the class incremental learning scenario where the agent is prone to ambiguities between old and new classes. With our proposed Knowledge-Aware contiNual learner (KAN), we demonstrate that considering the semantic similarity between old and new classes helps in achieving this balance. We show that being aware of existing knowledge helps in: (1) increasing the forward transfer from similar knowledge, (2) reducing the required capacity by leveraging existing knowledge, (3) protecting dissimilar knowledge, and (4) increasing robustness to the class order in the sequence. We evaluated sequences of similar tasks, dissimilar tasks, and a mix of both constructed from the two commonly used benchmarks for class-incremental learning; CIFAR-10 and CIFAR-100. Continual learning (CL) aims to build intelligent agents based on deep neural networks that can learn a sequence of tasks, use previous knowledge in future learning, and accumulate on it without forgetting. The main challenge in this paradigm is the stability-plasticity dilemma (Mermillod et al., 2013). While fixing all weights, highest stability, hinders learning new tasks. Finding the right balance between stability and plasticity is challenging. This sharpens the community's focus on the forgetting problem.

Inspired by the conventional pooling layers in convolutional neural networks, many recent works in the field of graph machine learning have introduced pooling operators to reduce the size of graphs. The great variety in the literature stems from the many possible strategies for coarsening a graph, which may depend on different assumptions on the graph structure or the specific downstream task. In this paper we propose a formal characterization of graph pooling based on three main operations, called selection, reduction, and connection, with the goal of unifying the literature under a common framework. Following this formalization, we introduce a taxonomy of pooling operators and categorize more than thirty pooling methods proposed in recent literature. We propose criteria to evaluate the performance of a pooling operator and use them to investigate and contrast the behavior of different classes of the taxonomy on a variety of tasks.

Federated learning (FL) has been facilitating privacy-preserving deep learning in many walks of life such as medical image classification, network intrusion detection, and so forth. Whereas it necessitates a central parameter server for model aggregation, which brings about delayed model communication and vulnerability to adversarial attacks. A fully decentralized architecture like Swarm Learning allows peer-to-peer communication among distributed nodes, without the central server. One of the most challenging issues in decentralized deep learning is that data owned by each node are usually non-independent and identically distributed (non-IID), causing time-consuming convergence of model training. To this end, we propose a decentralized learning model called Homogeneous Learning (HL) for tackling non-IID data with a self-attention mechanism. In HL, training performs on each round's selected node, and the trained model of a node is sent to the next selected node at the end of each round. Notably, for the selection, the self-attention mechanism leverages reinforcement learning to observe a node's inner state and its surrounding environment's state, and find out which node should be selected to optimize the training. We evaluate our method with various scenarios for an image classification task. The result suggests that HL can produce a better performance compared with standalone learning and greatly reduce both the total training rounds by 50.8% and the communication cost by 74.6% compared with random policy-based decentralized learning for training on non-IID data.

The complete freedom of expression in social media has its costs especially in spreading harmful and abusive content that may induce people to act accordingly. Therefore, the need of detecting automatically such a content becomes an urgent task that will help and enhance the efficiency in limiting this toxic spread. Compared to other Arabic dialects which are mostly based on MSA, the Tunisian dialect is a combination of many other languages like MSA, Tamazight, Italian and French. Because of its rich language, dealing with NLP problems can be challenging due to the lack of large annotated datasets. In this paper we are introducing a new annotated dataset composed of approximately 10k of comments. We provide an in-depth exploration of its vocabulary through feature engineering approaches as well as the results of the classification performance of machine learning classifiers like NB and SVM and deep learning models such as ARBERT, MARBERT and XLM-R.

In recent developments in the field of Computer Vision, a rise is seen in the use of transformer-based architectures. They are surpassing the state-of-the-art set by CNN architectures in accuracy but on the other hand, they are computationally very expensive to train from scratch. As these models are quite recent in the Computer Vision field, there is a need to study it's transfer learning capabilities and compare it with CNNs so that we can understand which architecture is better when applied to real world problems with small data. In this work, we follow a simple yet restrictive method for fine-tuning both CNN and Transformer models pretrained on ImageNet1K on CIFAR-10 and compare them with each other. We only unfreeze the last transformer/encoder or last convolutional block of a model and freeze all the layers before it while adding a simple MLP at the end for classification. This simple modification lets us use the raw learned weights of both these neural networks. From our experiments, we find out that transformers-based architectures not only achieve higher accuracy than CNNs but some transformers even achieve this feat with around 4 times lesser number of parameters.

In the genome biology research, regulatory genome modeling is an important topic for many regulatory downstream tasks, such as promoter classification, transaction factor binding sites prediction. The core problem is to model how regulatory elements interact with each other and its variability across different cell types. However, current deep learning methods often focus on modeling genome sequences of a fixed set of cell types and do not account for the interaction between multiple regulatory elements, making them only perform well on the cell types in the training set and lack the generalizability required in biological applications. In this work, we propose a simple yet effective approach for pre-training genome data in a multi-modal and self-supervised manner, which we call GeneBERT. Specifically, we simultaneously take the 1d sequence of genome data and a 2d matrix of (transcription factors x regions) as the input, where three pre-training tasks are proposed to improve the robustness and generalizability of our model. We pre-train our model on the ATAC-seq dataset with 17 million genome sequences. We evaluate our GeneBERT on regulatory downstream tasks across different cell types, including promoter classification, transaction factor binding sites prediction, disease risk estimation, and splicing sites prediction. Extensive experiments demonstrate the effectiveness of multi-modal and self-supervised pre-training for large-scale regulatory genomics data.

Task-oriented dialogue systems have been a promising area in the NLP field. Previous work showed the effectiveness of using a single GPT-2 based model to predict belief states and responses via causal language modeling. In this paper, we leverage multi-task learning techniques to train a GPT-2 based model on a more challenging dataset with multiple domains, multiple modalities, and more diversity in output formats. Using only a single model, our method achieves better performance on all sub-tasks, across domains, compared to task and domain-specific models. Furthermore, we evaluated several proposed strategies for GPT-2 based dialogue systems with comprehensive ablation studies, showing that all techniques can further improve the performance.

On the way towards general Visual Question Answering (VQA) systems that are able to answer arbitrary questions, the need arises for evaluation beyond single-metric leaderboards for specific datasets. To this end, we propose a browser-based benchmarking tool for researchers and challenge organizers, with an API for easy integration of new models and datasets to keep up with the fast-changing landscape of VQA. Our tool helps test generalization capabilities of models across multiple datasets, evaluating not just accuracy, but also performance in more realistic real-world scenarios such as robustness to input noise. Additionally, we include metrics that measure biases and uncertainty, to further explain model behavior. Interactive filtering facilitates discovery of problematic behavior, down to the data sample level. As proof of concept, we perform a case study on four models. We find that state-of-the-art VQA models are optimized for specific tasks or datasets, but fail to generalize even to other in-domain test sets, for example they cannot recognize text in images. Our metrics allow us to quantify which image and question embeddings provide most robustness to a model. All code is publicly available.