arXiv subjects

Weijia Zhang

Publications and source records attributed to Weijia Zhang.

80 records · Page 5Linked to original sources

arXiv2021

How much has the Sun influenced Northern Hemisphere temperature trends? An ongoing debate

To evaluate the role of Total Solar Irradiance (TSI) on Northern Hemisphere (NH) surface air temperature trends it is important to have reliable estimates of both quantities. 16 different TSI estimates were compiled from the literature. 1/2 of these estimates are low variability and 1/2 are high variability. 5 largely-independent methods for estimating NH temperature trends were evaluated using: 1) only rural weather stations; 2) all available stations whether urban or rural (the standard approach); 3) only sea surface temperatures; 4) tree-ring temperature proxies; 5) glacier length temperature proxies. The standard estimates using urban as well as rural stations were anomalous as they implied a much greater warming in recent decades than the other estimates. This suggests urbanization bias might still be a problem in current global temperature datasets despite the conclusions of some earlier studies. Still, all 5 estimates confirm it is currently warmer than the late 19th century, i.e., there has been some global warming since 1850. For the 5 estimates of NH temperatures, the contribution from direct solar forcing for all 16 estimates of TSI was evaluated using simple linear least-squares fitting. The role of human activity in recent warming was then calculated by fitting the residuals to the UN IPCC's recommended anthropogenic forcings time series. For all 5 NH temperature series, different TSI estimates implied everything from recent global warming being mostly human-caused to it being mostly natural. It seems previous studies (including the most recent IPCC reports) that had prematurely concluded the former failed to adequately consider all the relevant estimates of TSI and/or to satisfactorily address the uncertainties still associated with NH temperature trend estimates. Several recommendations are provided on how future research could more satisfactorily resolve these issues.

physics.ao-ph↗

arXiv2021

Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels using Variational Auto-Encoder

Multi-instance learning is a type of weakly supervised learning. It deals with tasks where the data is a set of bags and each bag is a set of instances. Only the bag labels are observed whereas the labels for the instances are unknown. An important advantage of multi-instance learning is that by representing objects as a bag of instances, it is able to preserve the inherent dependencies among parts of the objects. Unfortunately, most existing algorithms assume all instances to be \textit{identically and independently distributed}, which violates real-world scenarios since the instances within a bag are rarely independent. In this work, we propose the Multi-Instance Variational Auto-Encoder (MIVAE) algorithm which explicitly models the dependencies among the instances for predicting both bag labels and instance labels. Experimental results on several multi-instance benchmarks and end-to-end medical imaging datasets demonstrate that MIVAE performs better than state-of-the-art algorithms for both instance label and bag label prediction tasks.

cs.LG↗

arXiv2021

Treatment effect estimation with disentangled latent factors

Much research has been devoted to the problem of estimating treatment effects from observational data; however, most methods assume that the observed variables only contain confounders, i.e., variables that affect both the treatment and the outcome. Unfortunately, this assumption is frequently violated in real-world applications, since some variables only affect the treatment but not the outcome, and vice versa. Moreover, in many cases only the proxy variables of the underlying confounding factors can be observed. In this work, we first show the importance of differentiating confounding factors from instrumental and risk factors for both average and conditional average treatment effect estimation, and then we propose a variational inference approach to simultaneously infer latent factors from the observed variables, disentangle the factors into three disjoint sets corresponding to the instrumental, confounding, and risk factors, and use the disentangled factors for treatment effect estimation. Experimental results demonstrate the effectiveness of the proposed method on a wide range of synthetic, benchmark, and real-world datasets.

cs.LG↗

arXiv2021

Robust Multi-instance Learning with Stable Instances

Multi-instance learning (MIL) deals with tasks where data is represented by a set of bags and each bag is described by a set of instances. Unlike standard supervised learning, only the bag labels are observed whereas the label for each instance is not available to the learner. Previous MIL studies typically follow the i.i.d. assumption, that the training and test samples are independently drawn from the same distribution. However, such assumption is often violated in real-world applications. Efforts have been made towards addressing distribution changes by importance weighting the training data with the density ratio between the training and test samples. Unfortunately, models often need to be trained without seeing the test distributions. In this paper we propose possibly the first framework for addressing distribution change in MIL without requiring access to the unlabeled test data. Our framework builds upon identifying a novel connection between MIL and the potential outcome framework in causal effect estimation. Experimental results on synthetic distribution change datasets, real-world datasets with synthetic distribution biases and real distributional biased image classification datasets validate the effectiveness of our approach.

cs.LG↗

arXiv2021

A general framework for causal classification

In many applications, there is a need to predict the effect of an intervention on different individuals from data. For example, which customers are persuadable by a product promotion? which patients should be treated with a certain type of treatment? These are typical causal questions involving the effect or the change in outcomes made by an intervention. The questions cannot be answered with traditional classification methods as they only use associations to predict outcomes. For personalised marketing, these questions are often answered with uplift modelling. The objective of uplift modelling is to estimate causal effect, but its literature does not discuss when the uplift represents causal effect. Causal heterogeneity modelling can solve the problem, but its assumption of unconfoundedness is untestable in data. So practitioners need guidelines in their applications when using the methods. In this paper, we use causal classification for a set of personalised decision making problems, and differentiate it from classification. We discuss the conditions when causal classification can be resolved by uplift (and causal heterogeneity) modelling methods. We also propose a general framework for causal classification, by using off-the-shelf supervised methods for flexible implementations. Experiments have shown two instantiations of the framework work for causal classification and for uplift (causal heterogeneity) modelling, and are competitive with the other uplift (causal heterogeneity) modelling methods.

cs.LG↗

arXiv2021

Intelligent Electric Vehicle Charging Recommendation Based on Multi-Agent Reinforcement Learning

Electric Vehicle (EV) has become a preferable choice in the modern transportation system due to its environmental and energy sustainability. However, in many large cities, EV drivers often fail to find the proper spots for charging, because of the limited charging infrastructures and the spatiotemporally unbalanced charging demands. Indeed, the recent emergence of deep reinforcement learning provides great potential to improve the charging experience from various aspects over a long-term horizon. In this paper, we propose a framework, named Multi-Agent Spatio-Temporal Reinforcement Learning (Master), for intelligently recommending public accessible charging stations by jointly considering various long-term spatiotemporal factors. Specifically, by regarding each charging station as an individual agent, we formulate this problem as a multi-objective multi-agent reinforcement learning task. We first develop a multi-agent actor-critic framework with the centralized attentive critic to coordinate the recommendation between geo-distributed agents. Moreover, to quantify the influence of future potential charging competition, we introduce a delayed access strategy to exploit the knowledge of future charging competition during training. After that, to effectively optimize multiple learning objectives, we extend the centralized attentive critic to multi-critics and develop a dynamic gradient re-weighting strategy to adaptively guide the optimization direction. Finally, extensive experiments on two real-world datasets demonstrate that Master achieves the best comprehensive performance compared with nine baseline approaches.

cs.LG↗

arXiv2019

Semi-Supervised Hierarchical Recurrent Graph Neural Network for City-Wide Parking Availability Prediction

The ability to predict city-wide parking availability is crucial for the successful development of Parking Guidance and Information (PGI) systems. Indeed, the effective prediction of city-wide parking availability can improve parking efficiency, help urban planning, and ultimately alleviate city congestion. However, it is a non-trivial task for predicting citywide parking availability because of three major challenges: 1) the non-Euclidean spatial autocorrelation among parking lots, 2) the dynamic temporal autocorrelation inside of and between parking lots, and 3) the scarcity of information about real-time parking availability obtained from real-time sensors (e.g., camera, ultrasonic sensor, and GPS). To this end, we propose Semi-supervised Hierarchical Recurrent Graph Neural Network (SHARE) for predicting city-wide parking availability. Specifically, we first propose a hierarchical graph convolution structure to model non-Euclidean spatial autocorrelation among parking lots. Along this line, a contextual graph convolution block and a soft clustering graph convolution block are respectively proposed to capture local and global spatial dependencies between parking lots. Additionally, we adopt a recurrent neural network to incorporate dynamic temporal dependencies of parking lots. Moreover, we propose a parking availability approximation module to estimate missing real-time parking availabilities from both spatial and temporal domain. Finally, experiments on two real-world datasets demonstrate the prediction performance of SHARE outperforms seven state-of-the-art baselines.

cs.LG↗

arXiv2008

The Cambrian impact hypothesis

After a thorough research on the circumstantial changes and the great evolution of life in the Cambrian period, the author propounds such a hypothesis: During the Late Precambrian, about 500-600Ma, a celestial body impacted the Earth. The high temperature ended the great glaciation, facilitated the communication of biological information. The rapid change of Earth environment enkindled the genesis-control system, and released the HSP-90 variations. After the impact, benefited from the protection of the new ozone layer and the energy supplement of the aerobic respiration, those survived underground life exploded. They generated carapaces and complex metabolism to adjust to the new circumstance of high temperature and high pressure. This article uses a large amount of analyses and calculations, and illustrates that this hypothesis fits well with most of the important incidences in astronomic and geologic discoveries.

physics.gen-ph↗