Zhaoyu Wang

Bio: Zhaoyu Wang is an academic researcher from Tsinghua University. The author has contributed to research in topics: Supervised learning & Microclimate. The author has an hindex of 1, co-authored 1 publications receiving 98 citations.

Self-supervised Learning: Generative or Contrastive.

Abstract: Deep supervised learning has achieved great success in the last decade. However, its deficiencies of dependence on manual labels and vulnerability to attacks have driven people to explore a better solution. As an alternative, self-supervised learning attracts many researchers for its soaring performance on representation learning in the last several years. Self-supervised representation learning leverages input data itself as supervision and benefits almost all types of downstream tasks. In this survey, we take a look into new self-supervised learning methods for representation in computer vision, natural language processing, and graph learning. We comprehensively review the existing empirical methods and summarize them into three main categories according to their objectives: generative, contrastive, and generative-contrastive (adversarial). We further investigate related theoretical analysis work to provide deeper thoughts on how self-supervised learning works. Finally, we briefly discuss open problems and future directions for self-supervised learning. An outline slide for the survey is provided.

Impacts of Water Bodies on Microclimates and Outdoor Thermal Comfort: Implications for Sustainable Rural Revitalization

Abstract: Water is the source of life and the fundamental element of ecology, and climate is inseparable from water. To evaluate the influence of water-adaptive space in a traditional Weizi (polder village) settlement on its microclimate, the authors analyzed the morphological characteristics of such a polder village and applied the ENVI-met model to simulate the impact of water bodies and village morphological elements on human thermal comfort. This paper demonstrates the positive impact of water bodies on improving the thermal environment of a village and regulating its microclimate by quantifying the impact of morphological elements of the settlement on microclimate. The results indicate that: 1) The simulation model fits the actual measurements well, and the simulation accurately reflects experimental results; 2) In summer, the cooling effect of water bodies is better in the afternoon than in the morning, especially from 12:00 to 15:00. The cooling effect is significantly correlated with the distance to water bodies, i.e., the closer, the better; 3) Building density and man-made underlying surface are negatively correlated with temperature, humidity, and Physiological Equivalent Temperature value, while greening rate and water body rate are positively correlated with microclimate. Overall, water bodies can improve outdoor comfort in summer and thus should be protected and developed in rural planning and design. Villages can be built around water bodies for a maximized cooling effect, and microclimate comfort can be effectively improved by increasing green plants near the village center, and reducing man-made underlying surface and building density. The results of this study will guide the improvement of the habitat environment in the process of rural revitalization, as well as the protection and re-development of traditional villages.

A Survey on Contrastive Self-supervised Learning

Abstract: Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudo labels as supervision and use the learned representations for several downstream tasks. Specifically, contrastive learning has recently become a dominant component in self-supervised learning methods for computer vision, natural language processing (NLP), and other domains. It aims at embedding augmented versions of the same sample close to each other while trying to push away embeddings from different samples. This paper provides an extensive review of self-supervised methods that follow the contrastive approach. The work explains commonly used pretext tasks in a contrastive learning setup, followed by different architectures that have been proposed so far. Next, we have a performance comparison of different methods for multiple downstream tasks such as image classification, object detection, and action recognition. Finally, we conclude with the limitations of the current methods and the need for further techniques and future directions to make substantial progress.

A Survey on Contrastive Self-Supervised Learning

Abstract: Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudolabels as supervision and use the learned representations for several downstream tasks. Specifically, contrastive learning has recently become a dominant component in self-supervised learning for computer vision, natural language processing (NLP), and other domains. It aims at embedding augmented versions of the same sample close to each other while trying to push away embeddings from different samples. This paper provides an extensive review of self-supervised methods that follow the contrastive approach. The work explains commonly used pretext tasks in a contrastive learning setup, followed by different architectures that have been proposed so far. Next, we present a performance comparison of different methods for multiple downstream tasks such as image classification, object detection, and action recognition. Finally, we conclude with the limitations of the current methods and the need for further techniques and future directions to make meaningful progress.

Synthesis Lectures on Human Language Technologies

Abstract: Considerable progress has been made in recent years in the development of dialogue systems that support robust and efficient human–machine interaction using spoken language. Spoken dialogue technology allows various interactive applications to be built and used for practical purposes, and research focuses on issues that aim to increase the system’s communicative competence by including aspects of error correction, cooperation, multimodality, and adaptation in context. This book gives a comprehensive view of state-of-the-art techniques that are used to build spoken dialogue systems. It provides an overview of the basic issues such as system architectures, various dialogue management methods, system evaluation, and also surveys advanced topics concerning extensions of the basic model to more conversational setups. The goal of the book is to provide an introduction to the methods, problems, and solutions that are used in dialogue system development and evaluation. It presents dialogue modelling and system development issues relevant in both academic and industrial environments and also discusses requirements and challenges for advanced interaction management and future research. vi KEywoRDS Spoken dialogue systems, multimodality, evaluation, error-handling, dialogue management, statistical method v MC_Jok nen_FM. ndd Achorn Internat onal 10/10/2009 04:18AM

GLM-130B: An Open Bilingual Pre-trained Model

Abstract: We introduce GLM-130B, a bilingual (English and Chinese) pre-trained language model with 130 billion parameters. It is an attempt to open-source a 100B-scale model at least as good as GPT-3 and unveil how models of such a scale can be successfully pre-trained. Over the course of this effort, we face numerous unexpected technical and engineering challenges, particularly on loss spikes and disconvergence. In this paper, we introduce the training process of GLM-130B including its design choices, training strategies for both efficiency and stability, and engineering efforts. The resultant GLM-130B model offers significant outperformance over GPT-3 175B on a wide range of popular English benchmarks while the performance advantage is not observed in OPT-175B and BLOOM-176B. It also consistently and significantly outperforms ERNIE TITAN 3.0 260B -- the largest Chinese language model -- across related benchmarks. Finally, we leverage a unique scaling property of GLM-130B to reach INT4 quantization, without quantization aware training and with almost no performance loss, making it the first among 100B-scale models. More importantly, the property allows its effective inference on 4$\times$RTX 3090 (24G) or 8$\times$RTX 2080 Ti (11G) GPUs, the most ever affordable GPUs required for using 100B-scale models. The GLM-130B model weights are publicly accessible and its code, training logs, related toolkit, and lessons learned are open-sourced at https://github.com/THUDM/GLM-130B .

Pre-Trained Models: Past, Present and Future

Abstract: Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success and become a milestone in the field of artificial intelligence (AI). Owing to sophisticated pre-training objectives and huge model parameters, large-scale PTMs can effectively capture knowledge from massive labeled and unlabeled data. By storing knowledge into huge parameters and fine-tuning on specific tasks, the rich knowledge implicitly encoded in huge parameters can benefit a variety of downstream tasks, which has been extensively demonstrated via experimental verification and empirical analysis. It is now the consensus of the AI community to adopt PTMs as backbone for downstream tasks rather than learning models from scratch. In this paper, we take a deep look into the history of pre-training, especially its special relation with transfer learning and self-supervised learning, to reveal the crucial position of PTMs in the AI development spectrum. Further, we comprehensively review the latest breakthroughs of PTMs. These breakthroughs are driven by the surge of computational power and the increasing availability of data, towards four important directions: designing effective architectures, utilizing rich contexts, improving computational efficiency, and conducting interpretation and theoretical analysis. Finally, we discuss a series of open problems and research directions of PTMs, and hope our view can inspire and advance the future study of PTMs.