Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that can generalize to unseen distributions. ...Domain generalization (DG), i.e., out-of-distribution generalization, has attracted increasing interests in recent years. Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain. Great progress has been made in the area of domain generalization for years. This paper presents the first review of recent advances in this area. First, we provide a formal definition of domain generalization and discuss several related fields. We then thoroughly review the theories related to domain generalization and carefully analyze the theory behind generalization. We categorize recent algorithms into three classes: data manipulation, representation learning, and learning strategy, and present several popular algorithms in detail for each category. Third, we introduce the commonly used datasets, applications, and our open-sourced codebase for fair evaluation. Finally, we summarize existing literature and present some potential research topics for the future.
A significant amount of research effort has been put into finding variables that can identify students at risk based on activity records available in learning management systems (LMS). These ...variables often depend on the context, for example, the course structure, how the activities are assessed or whether the course is entirely online or a blended course. To the best of our knowledge, a predictive model that can generalize well to many different types of courses using data available in the LMS does not currently exist in the learning analytics literature. In this study, early prediction of students at risk is tackled by training a number of neural networks to predict which students would likely submit their assignments on time based on their activity up to two days before assignments’ due dates. Five different datasets that cover a total of 78 722 student enrolments in 5487 courses have been used in this study. In order to improve how well the neural networks generalize, our networks can perform different forms of feature engineering using course peers data. The different architectures of these networks have been compared to find the one with more predictive power. To validate the models trained from the networks, both new datasets and unseen examples extracted from the same datasets have been used for training. Our research show that adding contextual information results in better prediction accuracies and F1 scores. Our networks are able to give predictions with accuracies in the 67.46–81.63% range and F1 scores in the 71.30–83.09% range.
Deep generative models are a class of techniques that train deep neural networks to model the distribution of training samples. Research has fragmented into various interconnected approaches, each of ...which make trade-offs including run-time, diversity, and architectural restrictions. In particular, this compendium covers energy-based models, variational autoencoders, generative adversarial networks, autoregressive models, normalizing flows, in addition to numerous hybrid approaches. These techniques are compared and contrasted, explaining the premises behind each and how they are interrelated, while reviewing current state-of-the-art advances and implementations.
Bidirectional Encoder Representations from Transformers (BERT) has shown marvelous improvements across various NLP tasks, and its consecutive variants have been proposed to further improve the ...performance of the pre-trained language models. In this paper, we aim to first introduce the whole word masking (wwm) strategy for Chinese BERT, along with a series of Chinese pre-trained language models. Then we also propose a simple but effective model called MacBERT, which improves upon RoBERTa in several ways. Especially, we propose a new masking strategy called MLM as correction (Mac). To demonstrate the effectiveness of these models, we create a series of Chinese pre-trained language models as our baselines, including BERT, RoBERTa, ELECTRA, RBT, etc. We carried out extensive experiments on ten Chinese NLP tasks to evaluate the created Chinese pre-trained language models as well as the proposed MacBERT. Experimental results show that MacBERT could achieve state-of-the-art performances on many NLP tasks, and we also ablate details with several findings that may help future research. We open-source our pre-trained language models for further facilitating our research community.<xref ref-type="fn" rid="fn1"> 1
Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise. Therefore, ...detecting whether an example is out-of-distribution (OoD) is crucial to enable a system that can reject such samples or alert users. Recent works have made significant progress on OoD benchmarks consisting of small image datasets. However, many recent methods based on neural networks rely on training or tuning with both in-distribution and out-of-distribution data. The latter is generally hard to define a-priori, and its selection can easily bias the learning. We base our work on a popular method ODIN, proposing two strategies for freeing it from the needs of tuning with OoD data, while improving its OoD detection performance. We specifically propose to decompose confidence scoring as well as a modified input pre-processing method. We show that both of these significantly help in detection performance. Our further analysis on a larger scale image dataset shows that the two types of distribution shifts, specifically semantic shift and non-semantic shift, present a significant difference in the difficulty of the problem, providing an analysis of when ODIN-like strategies do or do not work.
Traffic forecasting is a particularly challenging application of spatiotemporal forecasting, due to the time-varying traffic patterns and the complicated spatial dependencies on road networks. To ...address this challenge, we learn the traffic network as a graph and propose a novel deep learning framework, Traffic Graph Convolutional Long Short-Term Memory Neural Network (TGC-LSTM), to learn the interactions between roadways in the traffic network and forecast the network-wide traffic state. We define the traffic graph convolution based on the physical network topology. The relationship between the proposed traffic graph convolution and the spectral graph convolution is also discussed. An L1-norm on graph convolution weights and an L2-norm on graph convolution features are added to the model's loss function to enhance the interpretability of the proposed model. Experimental results show that the proposed model outperforms baseline methods on two real-world traffic state datasets. The visualization of the graph convolution weights indicates that the proposed framework can recognize the most influential road segments in real-world traffic networks.
As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is ...facing efficiency and privacy challenges. Recently, federated learning (FL) has emerged as an alternative solution and continues to thrive in this new reality. Existing FL protocol designs have been shown to be vulnerable to adversaries within or outside of the system, compromising data privacy and system robustness. Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries. In this article, we conduct a comprehensive survey on privacy and robustness in FL over the past five years. Through a concise introduction to the concept of FL and a unique taxonomy covering: 1) threat models; 2) privacy attacks and defenses; and 3) poisoning attacks and defenses, we provide an accessible review of this important topic. We highlight the intuitions, key techniques, and fundamental assumptions adopted by various attacks and defenses. Finally, we discuss promising future research directions toward robust and privacy-preserving FL, and their interplays with the multidisciplinary goals of FL.
Fairness in deep learning has attracted tremendous attention recently, as deep learning is increasingly being used in high-stake decision making applications that affect individual lives. We provide ...a review covering recent progresses to tackle algorithmic fairness problems of deep learning from the computational perspective. Specifically, we show that interpretability can serve as a useful ingredient to diagnose the reasons that lead to algorithmic discrimination. We also discuss fairness mitigation approaches categorized according to three stages of deep learning life-cycle, aiming to push forward the area of fairness in deep learning and build genuinely fair and reliable deep learning systems.
Large language models (LLMs), such as ChatGPT and GPT4, are making new waves in the field of natural language processing and artificial intelligence, due to their emergent ability and ...generalizability. However, LLMs are black-box models, which often fall short of capturing and accessing factual knowledge. In contrast, Knowledge Graphs (KGs), Wikipedia, and Huapu for example, are structured knowledge models that explicitly store rich factual knowledge. KGs can enhance LLMs by providing external knowledge for inference and interpretability. Meanwhile, KGs are difficult to construct and evolve by nature, which challenges the existing methods in KGs to generate new facts and represent unseen knowledge. Therefore, it is complementary to unify LLMs and KGs together and, simultaneously, leverage their advantages. In this article, we present a forward-looking roadmap for the unification of LLMs and KGs. Our roadmap consists of three general frameworks, namely: 1) KG-enhanced LLMs, which incorporate KGs during the pre-training and inference phases of LLMs, or for the purpose of enhancing understanding of the knowledge learned by LLMs; 2) LLM-augmented KGs, that leverage LLMs for different KG tasks such as embedding, completion, construction, graph-to-text generation, and question answering; and 3) Synergized LLMs + KGs , in which LLMs and KGs play equal roles and work in a mutually beneficial way to enhance both LLMs and KGs for bidirectional reasoning driven by both data and knowledge. We review and summarize existing efforts within these three frameworks in our roadmap and pinpoint their future research directions.
Bitcoin has recently attracted considerable attention in the fields of economics, cryptography, and computer science due to its inherent nature of combining encryption technology and monetary units. ...This paper reveals the effect of Bayesian neural networks (BNNs) by analyzing the time series of Bitcoin process. We also select the most relevant features from Blockchain information that is deeply involved in Bitcoin's supply and demand and use them to train models to improve the predictive performance of the latest Bitcoin pricing process. We conduct the empirical study that compares the Bayesian neural network with other linear and non-linear benchmark models on modeling and predicting the Bitcoin process. Our empirical studies show that BNN performs well in predicting Bitcoin price time series and explaining the high volatility of the recent Bitcoin price.