Differential effect of interventions in patients with prediabetes stratified by a machine learning-based diabetes progression prediction model.

AIM: To investigate whether stratifying participants with prediabetes according to their diabetes progression risks (PR) could affect their responses to interventions. METHODS: We developed a machine learning-based model to predict the 1-year diabetes PR (ML-PR) with the least predictors. The model was developed and internally validated in participants with prediabetes in the Pinggu Study (a prospective population-based survey in suburban Beijing; n = 622). Patients from the Beijing Prediabetes Reversion Program cohort (a multicentre randomized control trial to evaluate the efficacy of lifestyle and/or pioglitazone on prediabetes reversion; n = 1936) were stratified to low-, medium- and high-risk groups using ML-PR. Different effect of four interventions within subgroups on prediabetes reversal and diabetes progression was assessed. RESULTS: Using least predictors including fasting plasma glucose, 2-h postprandial glucose after 75 g glucose administration, glycated haemoglobin, high-density lipoprotein cholesterol and triglycerides, and the ML algorithm XGBoost, ML-PR successfully predicted the 1-year progression of participants with prediabetes in the Pinggu study [internal area under the curve of the receiver operating characteristic curve 0.80 (0.72-0.89)] and Beijing Prediabetes Reversion Program [external area under the curve of the receiver operating characteristic curve 0.80 (0.74-0.86)]. In the high-risk group pioglitazone plus intensive lifestyle therapy significantly reduced diabetes progression by about 50% at year l and the end of the trial in the high-risk group compared with conventional lifestyle therapy with placebo. In the medium- or low-risk group, intensified lifestyle therapy, pioglitazone or their combination did not show any benefit on diabetes progression and prediabetes reversion. CONCLUSIONS: This study suggests personalized treatment for prediabetes according to their PR is necessary. ML-PR model with simple clinical variables may facilitate personal treatment strategies in participants with prediabetes.

An Annealing Mechanism for Adversarial Training Acceleration.

Despite the empirical success in various domains, it has been revealed that deep neural networks are vulnerable to maliciously perturbed input data that can dramatically degrade their performance. These are known as adversarial attacks. To counter adversarial attacks, adversarial training formulated as a form of robust optimization has been demonstrated to be effective. However, conducting adversarial training brings much computational overhead compared with standard training. In order to reduce the computational cost, we propose an annealing mechanism, annealing mechanism for adversarial training acceleration (Amata), to reduce the overhead associated with adversarial training. The proposed Amata is provably convergent, well-motivated from the lens of optimal control theory, and can be combined with existing acceleration methods to further enhance performance. It is demonstrated that, on standard datasets, Amata can achieve similar or better robustness with around 1/3-1/2 the computational time compared with traditional methods. In addition, Amata can be incorporated into other adversarial training acceleration algorithms (e.g., YOPO, Free, Fast, and ATTA), which leads to a further reduction in computational time on large-scale problems.

Adaptive Progressive Continual Learning.

Continual learning paradigm learns from a continuous stream of tasks in an incremental manner and aims to overcome the notorious issue: the catastrophic forgetting. In this work, we propose a new adaptive progressive network framework including two models for continual learning: Reinforced Continual Learning (RCL) and Bayesian Optimized Continual Learning with Attention mechanism (BOCL) to solve this fundamental issue. The core idea of this framework is to dynamically and adaptively expand the neural network structure upon the arrival of new tasks. RCL and BOCL employ reinforcement learning and Bayesian optimization to achieve it, respectively. An outstanding advantage of our proposed framework is that it will not forget the knowledge that has been learned through adaptively controlling the architecture. We propose effective ways of employing the learned knowledge in the two methods to control the size of the network. RCL employs previous knowledge directly while BOCL selectively utilizes previous knowledge (e.g., feature maps of previous tasks) via attention mechanism. The experiments on variants of MNIST, CIFAR-100 and Sequence of 5-Datasets demonstrate that our methods outperform the state-of-the-art in preventing catastrophic forgetting and fitting new tasks better under the same or less computing resource.

Spatio-Temporal Manifold Learning for Human Motions via Long-Horizon Modeling.

Data-driven modeling of human motions is ubiquitous in computer graphics and computer vision applications, such as synthesizing realistic motions or recognizing actions. Recent research has shown that such problems can be approached by learning a natural motion manifold using deep learning on a large amount data, to address the shortcomings of traditional data-driven approaches. However, previous deep learning methods can be sub-optimal for two reasons. First, the skeletal information has not been fully utilized for feature extraction. Unlike images, it is difficult to define spatial proximity in skeletal motions in the way that deep networks can be applied for feature extraction. Second, motion is time-series data with strong multi-modal temporal correlations between frames. On the one hand, a frame could be followed by several candidate frames leading to different motions; on the other hand, long-range dependencies exist where a number of frames in the beginning are correlated with a number of frames later. Ineffective temporal modeling would either under-estimate the multi-modality and variance, resulting in featureless mean motion or over-estimate them resulting in jittery motions, which is a major source of visual artifacts. In this paper, we propose a new deep network to tackle these challenges by creating a natural motion manifold that is versatile for many applications. The network has a new spatial component for feature extraction. It is also equipped with a new batch prediction model that predicts a large number of frames at once, such that long-term temporally-based objective functions can be employed to correctly learn the motion multi-modality and variances. With our system, long-duration motions can be predicted/synthesized using an open-loop setup where the motion retains the dynamics accurately. It can also be used for denoising corrupted motions and synthesizing new motions with given control signals. We demonstrate that our system can create superior results comparing to existing work in multiple applications.