The development of medical applications of machine learning has required manual annotation of data, often by medical experts. Yet, the availability of large-scale unannotated data provides opportunities for the development of better machine-learning models. In this Review, we highlight self-supervised methods and models for use in medicine and healthcare, and discuss the advantages and limitations of their application to tasks involving electronic health records and datasets of medical images, bioelectrical signals, and sequences and structures of genes and proteins. We also discuss promising applications of self-supervised learning for the development of models leveraging multimodal datasets, and the challenges in collecting unbiased data for their training. Self-supervised learning may accelerate the development of medical artificial intelligence.

The technical report presents our emotion recognition pipeline for high-dimensional emotion task (A-VB High) in The ACII Affective Vocal Bursts (A-VB) 2022 Workshop \& Competition. Our proposed method contains three stages. Firstly, we extract the latent features from the raw audio signal and its Mel-spectrogram by self-supervised learning methods. Then, the features from the raw signal are fed to the self-relation attention and temporal awareness (SA-TA) module for learning the valuable information between these latent features. Finally, we concatenate all the features and utilize a fully-connected layer to predict each emotion's score. By empirical experiments, our proposed method achieves a mean concordance correlation coefficient (CCC) of 0.7295 on the test set, compared to 0.5686 on the baseline model. The code of our method is available at https://github.com/linhtd812/A-VB2022.

While the distribution patterns of cold-water corals, such as Paragorgia arborea, have received increasing attention in recent studies, little is known about their in situ activity patterns. In this paper, we examine polyp activity in P. arborea using machine learning techniques to analyze high-resolution time series data and photographs obtained from an autonomous lander cluster deployed in the Stjernsund, Norway. An interactive illustration of the models derived in this paper is provided online as supplementary material. We find that the best predictor of the degree of extension of the coral polyps is current direction with a lag of three hours. Other variables that are not directly associated with water currents, such as temperature and salinity, offer much less information concerning polyp activity. Interestingly, the degree of polyp extension can be predicted more reliably by sampling the laminar flows in the water column above the measurement site than by sampling the more turbulent flows in the direct vicinity of the corals. Our results show that the activity patterns of the P. arborea polyps are governed by the strong tidal current regime of the Stjernsund. It appears that P. arborea does not react to shorter changes in the ambient current regime but instead adjusts its behavior in accordance with the large-scale pattern of the tidal cycle itself in order to optimize nutrient uptake.

Continual Learning (CL) sequentially learns new tasks like human beings, with the goal to achieve better Stability (S, remembering past tasks) and Plasticity (P, adapting to new tasks). Due to the fact that past training data is not available, it is valuable to explore the influence difference on S and P among training examples, which may improve the learning pattern towards better SP. Inspired by Influence Function (IF), we first study example influence via adding perturbation to example weight and computing the influence derivation. To avoid the storage and calculation burden of Hessian inverse in neural networks, we propose a simple yet effective MetaSP algorithm to simulate the two key steps in the computation of IF and obtain the S- and P-aware example influence. Moreover, we propose to fuse two kinds of example influence by solving a dual-objective optimization problem, and obtain a fused influence towards SP Pareto optimality. The fused influence can be used to control the update of model and optimize the storage of rehearsal. Empirical results show that our algorithm significantly outperforms state-of-the-art methods on both task- and class-incremental benchmark CL datasets.

Since 2021, with the emergence of CLIP, contrastive pre-training has been extended to supervised learning with image-text pairs. The purpose of this extension is to improve the transferability of learned visual features by aligning them to the corresponding text features, as text features are proved to be highly transferrable in GPT-3. By this extension, visual models could be adapted to downstream tasks in a zero/few-shot learning manner with good performances and data-efficiency. The original CLIP pre-training is image-level, and the learned features are mainly used for image-level downstream tasks, e.g.

One of the ultimate goals of Artificial Intelligence is to learn generalised and human interpretable knowledge from raw data. Existing neuro-symbolic approaches partly tackle this problem by using manually engineered symbolic knowledge to improve the training of a neural network. In the few cases where symbolic knowledge is learned from raw data, this knowledge lacks the expressivity required to solve complex problems. In this paper, we introduce Neuro-Symbolic Inductive Learner (NSIL), an approach that trains a neural network to extract latent concepts from raw data, whilst learning symbolic knowledge that solves complex problems, defined in terms of these latent concepts. The novelty of our approach is a method for biasing a symbolic learner to learn improved knowledge, based on the in-training performance of both neural and symbolic components. We evaluate NSIL on two problem domains that require learning knowledge with different levels of complexity. Our experimental results demonstrate that NSIL learns knowledge of increased expressivity than what can be learned by the closest neuro-symbolic baseline systems, whilst outperforming them and other pure differentiable baseline models in terms of accuracy and data efficiency.

Active learning, which effectively collects informative unlabeled data for annotation, reduces the demand for labeled data. In this work, we propose to retrieve unlabeled samples with a local sensitivity and hardness-aware acquisition function. The proposed method generates data copies through local perturbations and selects data points whose predictive likelihoods diverge the most from their copies. We further empower our acquisition function by injecting the select-worst case perturbation. Our method achieves consistent gains over the commonly used active learning strategies in various classification tasks. Furthermore, we observe consistent improvements over the baselines on the study of prompt selection in prompt-based few-shot learning. These experiments demonstrate that our acquisition guided by local sensitivity and hardness can be effective and beneficial for many NLP tasks.

Applied mathematics and machine computations have raised a lot of hope since the recent success of supervised learning. Many practitioners in industries have been trying to switch from their old paradigms to machine learning. Interestingly, those data scientists spend more time scrapping, annotating and cleaning data than fine-tuning models. This thesis is motivated by the following question: can we derive a more generic framework than the one of supervised learning in order to learn from clutter data? This question is approached through the lens of weakly supervised learning, assuming that the bottleneck of data collection lies in annotation. We model weak supervision as giving, rather than a unique target, a set of target candidates. We argue that one should look for an ``optimistic'' function that matches most of the observations. This allows us to derive a principle to disambiguate partial labels. We also discuss the advantage to incorporate unsupervised learning techniques into our framework, in particular manifold regularization approached through diffusion techniques, for which we derived a new algorithm that scales better with input dimension then the baseline method. Finally, we switch from passive to active weakly supervised learning, introducing the ``active labeling'' framework, in which a practitioner can query weak information about chosen data. Among others, we leverage the fact that one does not need full information to access stochastic gradients and perform stochastic gradient descent.

In this paper, we analyze the impact of data freshness on real-time supervised learning, where a neural network is trained to infer a time-varying target (e.g., the position of the vehicle in front) based on features (e.g., video frames) observed at a sensing node (e.g., camera or lidar). One might expect that the performance of real-time supervised learning degrades monotonically as the feature becomes stale. Using an information-theoretic analysis, we show that this is true if the feature and target data sequence can be closely approximated as a Markov chain; it is not true if the data sequence is far from Markovian. Hence, the prediction error of real-time supervised learning is a function of the Age of Information (AoI), where the function could be non-monotonic. Several experiments are conducted to illustrate the monotonic and non-monotonic behaviors of the prediction error. To minimize the inference error in real-time, we propose a new "selection-from-buffer" model for sending the features, which is more general than the "generate-at-will" model used in earlier studies. By using Gittins and Whittle indices, low-complexity scheduling strategies are developed to minimize the inference error, where a new connection between the Gittins index theory and Age of Information (AoI) minimization is discovered. These scheduling results hold (i) for minimizing general AoI functions (monotonic or non-monotonic) and (ii) for general feature transmission time distributions. Data-driven evaluations are presented to illustrate the benefits of the proposed scheduling algorithms.

With the rising participation of the common mass in social media, it is increasingly common now for policymakers/journalists to create online polls on social media to understand the political leanings of people in specific locations. The caveat here is that only influential people can make such an online polling and reach out at a mass scale. Further, in such cases, the distribution of voters is not controllable and may be, in fact, biased. On the other hand,if we can interpret the publicly available data over social media to probe the political inclination of users, we will be able to have controllable insights about the survey population, keep the cost of survey low and also collect publicly available data without involving the concerned persons. Hence we introduce a self-attentive semi-supervised framework for political inclination detection to further that objective. The advantage of our model is that it neither needs huge training data nor does it need to store social network parameters. Nevertheless, it achieves an accuracy of 93.7\% with no annotated data; further, with only a few annotated examples per class it achieves competitive performance. We found that the model is highly efficient even in resource-constrained settings, and insights drawn from its predictions match the manual survey outcomes when applied to diverse real-life scenarios.