Now it is still a challenge to compress high-throughput hyperspectral tensor image data on lightweight air-carried/spaceborne remote sensing systems, primarily due to insufficient computational resources and limited transmission bandwidth. To address this challenge, we propose a bit-level tensor data compression network (BTC-Net) that provides higher compression performance by leveraging a data-driven lightweight quantized neural encoder with two-stage bit compression. The BTC-Net achieves semantic near-lossless high reconstruction quality at low compression bit rates thanks to its optimized decoder, which uses a channel-wise attention-based enhancement module to recover hyperspectral tensor data. Experimental results on different hyperspectral datasets show that the BTC-Net could achieve an extremely low compression bit rate of fewer than 0.04 bits per pixel per band (bpppb) with state-of-the-art reconstruction performances. The demo of BTC-Net will be publicly available online at: https://github.com/zx20173646/BTCNet.

The click-through rate (CTR) prediction task is to predict whether a user will click on the recommended item. As mind-boggling amounts of data are produced online daily, accelerating CTR prediction model training is critical to ensuring an up-to-date model and reducing the training cost. One approach to increase the training speed is to apply large batch training. However, as shown in computer vision and natural language processing tasks, training with a large batch easily suffers from the loss of accuracy. Our experiments show that previous scaling rules fail in the training of CTR prediction neural networks. To tackle this problem, we first theoretically show that different frequencies of ids make it challenging to scale hyperparameters when scaling the batch size. To stabilize the training process in a large batch size setting, we develop the adaptive Column-wise Clipping (CowClip). It enables an easy and effective scaling rule for the embeddings, which keeps the learning rate unchanged and scales the L2 loss. We conduct extensive experiments with four CTR prediction networks on two real-world datasets and successfully scaled 128 times the original batch size without accuracy loss. In particular, for CTR prediction model DeepFM training on the Criteo dataset, our optimization framework enlarges the batch size from 1K to 128K with over 0.1% AUC improvement and reduces training time from 12 hours to 10 minutes on a single V100 GPU. Our code locates at github.com/bytedance/LargeBatchCTR.

Upper limb rehabilitation robots are mainly used as a physical therapy method to passively or actively train the affected side. However, they are rarely implemented in accordance with the occupational therapy theory, which is dedicated to improving the sensorimotor coordination of hemiplegic patients by considering both healthy and affected limbs. To realize the occupational therapy concept in robot-assisted upper limb rehabilitation, we propose a new human-robot collaboration framework for hemiplegic patients that integrates healthy/affected limbs and robot. The strategy aims at achieving patient-specific movement capabilities and improving the participation of the affected limb during rehabilitation. To accomplish this task, we have addressed two essential issues: accurate motion estimation of the healthy limb and the rehabilitation trajectory learning technique. The posture estimation is achieved by introducing the calibration model to reduce static and time dependent errors during the measurement. We also introduce a force term to the conventional imitation learning method to improve the adaptability in integrating the affected side in cooperation with the robot. Various experiments have been conducted to validate the feasibility and effectiveness of our proposed dual-arm collaboration strategy.

ByteDance offers several massively popular products such as TikTok, Jinri Toutiao and Douyin for creating, sharing and discovering a variety of content, in which recommendation plays an indispensable role for helping billions of users to interact with highly personalized content. The personalized experience in products largely comes from the ability of sophisticated machine learning models to make accurate predictions based on users' interests and one key component in such systems is the user profile service.In this paper, we introduce Instance Profile Service (IPS), a large scale distributed system for managing unstructured profile data as well as serving various feature computations at ByteDance. Different products leverage IPS in many different ways and place various demands on the system, in terms of complex computation logic and latency requirements. One major challenge in the design of a large scale user profile system is how to strike the right balance among efficiency, scalability, reliability and versatility. With deliberated choices made on its design and implementation, we demonstrate IPS can provide a simple yet flexible solution to all these products while meeting the targeted high availability and performance goals. At ByteDance, IPS has successfully replaced many legacy profile systems and runs on thousands of machines. One of our largest production instances can process a hundred million feature queries and tens of millions writes per second.

Coronavirus disease 2019 (COVID-19) has spread rapidly worldwide, causing significant mortality. There is a mechanistic relationship between intracellular coronavirus replication and deregulated autophagosome-lysosome system. We performed transcriptome analysis of peripheral blood mononuclear cells (PBMCs) from COVID-19 patients and identified the aberrant upregulation of genes in the lysosome pathway. We further determined the capability of two circulating markers, namely microtubule-associated proteins 1A/1B light chain 3B (LC3B) and (p62/SQSTM1) p62, both of which depend on lysosome for degradation, in predicting the emergence of moderate-to-severe disease in COVID-19 patients requiring hospitalization for supplemental oxygen therapy. Logistic regression analyses showed that LC3B was associated with moderate-to-severe COVID-19, independent of age, sex and clinical risk score. A decrease in LC3B concentration <5.5 ng/ml increased the risk of oxygen and ventilatory requirement (adjusted odds ratio: 4.6; 95% CI: 1.1-22.0; P = 0.04). Serum concentrations of p62 in the moderate-to-severe group were significantly lower in patients aged 50 or below. In conclusion, lysosome function is deregulated in PBMCs isolated from COVID-19 patients, and the related biomarker LC3B may serve as a novel tool for stratifying patients with moderate-to-severe COVID-19 from those with asymptomatic or mild disease. COVID-19 patients with a decrease in LC3B concentration <5.5 ng/ml will require early hospital admission for supplemental oxygen therapy and other respiratory support.

Penalty function method is one of the most popular used Constraint Handling Techniques for Evolutionary Algorithms (EAs) solution selecting, whose performance is mainly determined by penalty parameters. This paper tries to study the penalty parameter from the aspect of problem characteristics, i.e., to construct a corresponding relationship between the problems and the penalty parameters. The experimental results confirm the relationship, which provides valuable reference for future algorithm design.

A new approach to overcome the problem caused by illumination variation in face recognition is proposed in this paper. Active Near-Infrared (Near-IR) illumination projected by a Light Emitting Diode (LED) light source is used to provide a constant illumination. The difference between two face images captured when the LED light is on and off respectively, is the image of a face under just the LED illumination, and is independent of ambient illumination. In preliminary experiments with various ambient illuminations, significantly better results are achieved for both automatic and semi-automatic face recognition experiments on LED illuminated faces than on face images under ambient illuminations. 1