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

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.

A Survey on Contrastive Self-Supervised Learning

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

https://www.morganclaypool.com/doi/suppl/10.2200/S00509ED1V01Y201305HLT023/suppl_file/Dagan_Ch1.pdf

Synthesis Lectures on Human Language Technologies

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 .

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

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.

Pre-Trained Models: Past, Present and Future

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.

Self-supervised Learning: Generative or Contrastive.

Deep supervised learning has achieved great success in the last decade. However, its defects of heavy dependence on manual labels and vulnerability to attacks have driven people to find other paradigms. As an alternative, self-supervised learning (SSL) 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 collect related theoretical analyses on self-supervised learning to provide deeper thoughts on why 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.

Self-supervised Learning: Generative or Contrastive

Self-supervised learning (SSL) has been extensively explored in recent years. Particularly, generative SSL has seen emerging success in natural language processing and other fields, such as the wide adoption of BERT and GPT. Despite this, contrastive learning---which heavily relies on structural data augmentation and complicated training strategies---has been the dominant approach in graph SSL, while the progress of generative SSL on graphs, especially graph autoencoders (GAEs), has thus far not reached the potential as promised in other fields. In this paper, we identify and examine the issues that negatively impact the development of GAEs, including their reconstruction objective, training robustness, and error metric. We present a masked graph autoencoder GraphMAE (code is publicly available at https://github.com/THUDM/GraphMAE) that mitigates these issues for generative self-supervised graph learning. Instead of reconstructing structures, we propose to focus on feature reconstruction with both a masking strategy and scaled cosine error that benefit the robust training of GraphMAE. We conduct extensive experiments on 21 public datasets for three different graph learning tasks. The results manifest that GraphMAE---a simple graph autoencoder with our careful designs---can consistently generate outperformance over both contrastive and generative state-of-the-art baselines. This study provides an understanding of graph autoencoders and demonstrates the potential of generative self-supervised learning on graphs.

/pdf/graphmae-self-supervised-masked-graph-autoencoders-274x9la9.pdf

GraphMAE: Self-Supervised Masked Graph Autoencoders

WeChat is the largest social instant messaging platform in China with 1.1 billion monthly active users.“Top Stories“ is a kind of novel friend-enhanced recommendation engine in WeChat, in which users can read articles based on both their own and their friends' preferences. Specifically, when a user reads an article by opening it, the “click” behavior is private. Besides, if the user clicks the wow button, (only) her/his direct connections will be aware of this action/preference. Based on the unique billion-scale WeChat data, we aim to understand user preferences and wow diffusion in Top Stories at different levels. We have some interesting discoveries. For instance, the wow probability of one user is negatively correlated with the number of connected components that are formed by her/his active friends, but the click probability is the opposite. We further study to what extent users wow and click behavior can be predicted from their social connections. To address it, we present a hierarchical graph representation learning based model ProHENE, which is capable of capturing the structured based social observations discovered above. Our experiments show that the proposed method can significantly improve the prediction performance compared with alternative methods.

Understanding WeChat User Preferences and “Wow” Diffusion

Graph representation learning aims to learn low-dimensional node embeddings for graphs. It is used in several real-world applications such as social network analysis and large-scale recommender systems. In this paper, we introduce CogDL, an extensive research toolkit for deep learning on graphs that allows researchers and developers to easily conduct experiments and build applications. It provides standard training and evaluation for the most important tasks in the graph domain, including node classification, link prediction, graph classification, and other graph tasks. For each task, it offers implementations of state-of-the-art models. The models in our toolkit are divided into two major parts, graph embedding methods and graph neural networks. Most of the graph embedding methods learn node-level or graph-level representations in an unsupervised way and preserves the graph properties such as structural information, while graph neural networks capture node features and work in semi-supervised or self-supervised settings. All models implemented in our toolkit can be easily reproducible for leaderboard results. Most models in CogDL are developed on top of PyTorch, and users can leverage the advantages of PyTorch to implement their own models. Furthermore, we demonstrate the effectiveness of CogDL for real-world applications in AMiner, which is a large academic database and system.

Zhenyu Hou

Papers

Self-supervised Learning: Generative or Contrastive.

Self-supervised Learning: Generative or Contrastive

GraphMAE: Self-Supervised Masked Graph Autoencoders

Understanding WeChat User Preferences and “Wow” Diffusion

CogDL: An Extensive Toolkit for Deep Learning on Graphs