arXiv subjects

Fei Wang

Publications and source records attributed to Fei Wang.

At least 559 records · Page 31Linked to original sources

arXiv2021

Long-Range Superconducting Proximity Effect in Nickel Nanowires

When a ferromagnet is placed in contact with a superconductor, owing to incompatible spin order, the Cooper pairs from the superconductor cannot survive more than one or two nanometers inside the ferromagnet. This is confirmed in the measurements of ferromagnetic nickel (Ni) nanowires contacted by superconducting niobium (Nb) leads. However, when a 3 nm thick copper oxide (CuO) buffer layer made by exposing an evaporated or a sputtered 3 nm Cu film to air, is inserted between the Nb electrodes and the Ni wire, the spatial extent of the superconducting proximity range is dramatically increased from 2 to a few tens of nanometers. Scanning transmission electron microscope study confirms the formation of a 3 nm thick CuO layer when an evaporated Cu film is exposed to air. Magnetization measurements of such a 3 nm CuO film on a SiO2/Si substrate and on Nb/SiO2/Si show clear evidence of ferromagnetism. One way to understand the long-range proximity effect in the Ni nanowire is that the CuO buffer layer with ferromagnetism facilitates the conversion of singlet superconductivity in Nb into triplet supercurrent along the Ni nanowires.

cond-mat.supr-con↗

arXiv2021

Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring

The success of the state-of-the-art video deblurring methods stems mainly from implicit or explicit estimation of alignment among the adjacent frames for latent video restoration. However, due to the influence of the blur effect, estimating the alignment information from the blurry adjacent frames is not a trivial task. Inaccurate estimations will interfere the following frame restoration. Instead of estimating alignment information, we propose a simple and effective deep Recurrent Neural Network with Multi-scale Bi-directional Propagation (RNN-MBP) to effectively propagate and gather the information from unaligned neighboring frames for better video deblurring. Specifically, we build a Multi-scale Bi-directional Propagation~(MBP) module with two U-Net RNN cells which can directly exploit the inter-frame information from unaligned neighboring hidden states by integrating them in different scales. Moreover, to better evaluate the proposed algorithm and existing state-of-the-art methods on real-world blurry scenes, we also create a Real-World Blurry Video Dataset (RBVD) by a well-designed Digital Video Acquisition System (DVAS) and use it as the training and evaluation dataset. Extensive experimental results demonstrate that the proposed RBVD dataset effectively improves the performance of existing algorithms on real-world blurry videos, and the proposed algorithm performs favorably against the state-of-the-art methods on three typical benchmarks. The code is available at https://github.com/XJTU-CVLAB-LOWLEVEL/RNN-MBP.

eess.IV↗

arXiv2021

Incentive Compatible Pareto Alignment for Multi-Source Large Graphs

In this paper, we focus on learning effective entity matching models over multi-source large-scale data. For real applications, we relax typical assumptions that data distributions/spaces, or entity identities are shared between sources, and propose a Relaxed Multi-source Large-scale Entity-matching (RMLE) problem. Challenges of the problem include 1) how to align large-scale entities between sources to share information and 2) how to mitigate negative transfer from joint learning multi-source data. What's worse, one practical issue is the entanglement between both challenges. Specifically, incorrect alignments may increase negative transfer; while mitigating negative transfer for one source may result in poorly learned representations for other sources and then decrease alignment accuracy. To handle the entangled challenges, we point out that the key is to optimize information sharing first based on Pareto front optimization, by showing that information sharing significantly influences the Pareto front which depicts lower bounds of negative transfer. Consequently, we proposed an Incentive Compatible Pareto Alignment (ICPA) method to first optimize cross-source alignments based on Pareto front optimization, then mitigate negative transfer constrained on the optimized alignments. This mechanism renders each source can learn based on its true preference without worrying about deteriorating representations of other sources. Specifically, the Pareto front optimization encourages minimizing lower bounds of negative transfer, which optimizes whether and which to align. Comprehensive empirical evaluation results on four large-scale datasets are provided to demonstrate the effectiveness and superiority of ICPA. Online A/B test results at a search advertising platform also demonstrate the effectiveness of ICPA in production environments.

stat.ML↗

arXiv2021

Gluino-SUGRA scenarios in light of FNAL muon g-2 anomaly

Gluino-SUGRA ($\tilde{g}$SUGRA), which is an economical extension of the predictive mSUGRA, adopts much heavier gluino mass parameter than other gauginos mass parameters and universal scalar mass parameter at the unification scale. It can elegantly reconcile the experimental results on the Higgs boson mass, the muon $g-2$, the null results in search for supersymmetry at the LHC and the results from B-physics. In this work, we propose several new ways to generate large gaugino hierarchy (i.e. $M_3\gg M_1,M_2$) for $\tilde{g}$SUGRA model building and then discuss in detail the implications of the new muon $g-2$ results with the updated LHC constraints on such $\tilde{g}$SUGRA scenarios. We obtain the following observations: (i) For the most interesting $M_1=M_2$ case at the GUT scale with a viable bino-like dark matter, the $\tilde{g}$SUGRA can explain the muon $g-2$ anomaly at $1σ$ level and be consistent with the updated LHC constraints for $6\leq M_3/M_1 \leq 9$ at the GUT scale; (ii) For $M_1:M_2=5:1$ at the GUT scale with wino-like dark matter, the $\tilde{g}$SUGRA model can explain the muon $g-2$ anomaly at $2σ$ level and be consistent with the updated LHC constraints for $3\leq M_3/M_1 \leq 3.2$ at the GUT scale; (iii) For $M_1:M_2=3:2$ at the GUT scale with mixed bino-wino dark matter, the $\tilde{g}$SUGRA model can explain the muon $g-2$ anomaly at $1σ$ level and be consistent with the updated LHC constraints for $6.9\leq M_3/M_1 \leq 7.5$ at the GUT scale. Although the choice of heavy gluino will always increase the FT involved, some of the $1σ/2σ$ survived points of $Δa_μ^{combine}$ can still allow low EWFT of order several hundreds and be fairly natural. Constraints from (dimension-five operator induced) proton decay are also discussed.

hep-ph↗

arXiv2021

Giant topological Hall effect in centrosymmetric tetragonal Mn2-xZnxSb

Topological magnetism typically appears in noncentrosymmetric compounds or compounds with geometric frustration. Here we report the effective tuning of magnetism in centrosymmetric tetragonal Mn2-xZnxSb by Zn substitution. The magnetism is found to be closely coupled to the transport properties, giving rise to to a very large topological hall effect is possibly associated with topological magnetism. Our finding suggests Mn2-xZnxSb is a candidate material for the centrosymmetric tetragonal topological magnetic system, offers opportunities for studying and tuning spin textures and developing near room temperature spin-based devices.

cond-mat.mtrl-sci↗

arXiv2021

ViTAS: Vision Transformer Architecture Search

Vision transformers (ViTs) inherited the success of NLP but their structures have not been sufficiently investigated and optimized for visual tasks. One of the simplest solutions is to directly search the optimal one via the widely used neural architecture search (NAS) in CNNs. However, we empirically find this straightforward adaptation would encounter catastrophic failures and be frustratingly unstable for the training of superformer. In this paper, we argue that since ViTs mainly operate on token embeddings with little inductive bias, imbalance of channels for different architectures would worsen the weight-sharing assumption and cause the training instability as a result. Therefore, we develop a new cyclic weight-sharing mechanism for token embeddings of the ViTs, which enables each channel could more evenly contribute to all candidate architectures. Besides, we also propose identity shifting to alleviate the many-to-one issue in superformer and leverage weak augmentation and regularization techniques for more steady training empirically. Based on these, our proposed method, ViTAS, has achieved significant superiority in both DeiT- and Twins-based ViTs. For example, with only $1.4$G FLOPs budget, our searched architecture has $3.3\%$ ImageNet-$1$k accuracy than the baseline DeiT. With $3.0$G FLOPs, our results achieve $82.0\%$ accuracy on ImageNet-$1$k, and $45.9\%$ mAP on COCO$2017$ which is $2.4\%$ superior than other ViTs.

cs.CV↗

arXiv2021

Clinical Evidence Engine: Proof-of-Concept For A Clinical-Domain-Agnostic Decision Support Infrastructure

Abstruse learning algorithms and complex datasets increasingly characterize modern clinical decision support systems (CDSS). As a result, clinicians cannot easily or rapidly scrutinize the CDSS recommendation when facing a difficult diagnosis or treatment decision in practice. Over-trust or under-trust are frequent. Prior research has explored supporting such assessments by explaining DST data inputs and algorithmic mechanisms. This paper explores a different approach: Providing precisely relevant, scientific evidence from biomedical literature. We present a proof-of-concept system, Clinical Evidence Engine, to demonstrate the technical and design feasibility of this approach across three domains (cardiovascular diseases, autism, cancer). Leveraging Clinical BioBERT, the system can effectively identify clinical trial reports based on lengthy clinical questions (e.g., "risks of catheter infection among adult patients in intensive care unit who require arterial catheters, if treated with povidone iodine-alcohol"). This capability enables the system to identify clinical trials relevant to diagnostic/treatment hypotheses -- a clinician's or a CDSS's. Further, Clinical Evidence Engine can identify key parts of a clinical trial abstract, including patient population (e.g., adult patients in intensive care unit who require arterial catheters), intervention (povidone iodine-alcohol), and outcome (risks of catheter infection). This capability opens up the possibility of enabling clinicians to 1) rapidly determine the match between a clinical trial and a clinical question, and 2) understand the result and contexts of the trial without extensive reading. We demonstrate this potential by illustrating two example use scenarios of the system. We discuss the idea of designing DST explanations not as specific to a DST or an algorithm, but as a domain-agnostic decision support infrastructure.

cs.AI↗

arXiv2021

Persona Authentication through Generative Dialogue

In this paper we define and investigate the problem of \emph{persona authentication}: learning a conversational policy to verify the consistency of persona models. We propose a learning objective and prove (under some mild assumptions) that local density estimators trained under this objective maximize the mutual information between persona information and dialog trajectory. Based on the proposed objective, we develop a method of learning an authentication model that adaptively outputs personalized questions to reveal the underlying persona of its partner throughout the course of multi-turn conversation. Experiments show that our authentication method discovers effective question sequences that generalize to unseen persona profiles.

cs.CL↗

arXiv2021

Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning

Federated learning (FL) has gain growing interests for its capability of learning from distributed data sources collectively without the need of accessing the raw data samples across different sources. So far FL research has mostly focused on improving the performance, how the algorithmic disparity will be impacted for the model learned from FL and the impact of algorithmic disparity on the utility inconsistency are largely unexplored. In this paper, we propose an FL framework to jointly consider performance consistency and algorithmic fairness across different local clients (data sources). We derive our framework from a constrained multi-objective optimization perspective, in which we learn a model satisfying fairness constraints on all clients with consistent performance. Specifically, we treat the algorithm prediction loss at each local client as an objective and maximize the worst-performing client with fairness constraints through optimizing a surrogate maximum function with all objectives involved. A gradient-based procedure is employed to achieve the Pareto optimality of this optimization problem. Theoretical analysis is provided to prove that our method can converge to a Pareto solution that achieves the min-max performance with fairness constraints on all clients. Comprehensive experiments on synthetic and real-world datasets demonstrate the superiority that our approach over baselines and its effectiveness in achieving both fairness and consistency across all local clients.

cs.LG↗

arXiv2021

SCEHR: Supervised Contrastive Learning for Clinical Risk Prediction using Electronic Health Records

Contrastive learning has demonstrated promising performance in image and text domains either in a self-supervised or a supervised manner. In this work, we extend the supervised contrastive learning framework to clinical risk prediction problems based on longitudinal electronic health records (EHR). We propose a general supervised contrastive loss $\mathcal{L}_{\text{Contrastive Cross Entropy} } + λ\mathcal{L}_{\text{Supervised Contrastive Regularizer}}$ for learning both binary classification (e.g. in-hospital mortality prediction) and multi-label classification (e.g. phenotyping) in a unified framework. Our supervised contrastive loss practices the key idea of contrastive learning, namely, pulling similar samples closer and pushing dissimilar ones apart from each other, simultaneously by its two components: $\mathcal{L}_{\text{Contrastive Cross Entropy} }$ tries to contrast samples with learned anchors which represent positive and negative clusters, and $\mathcal{L}_{\text{Supervised Contrastive Regularizer}}$ tries to contrast samples with each other according to their supervised labels. We propose two versions of the above supervised contrastive loss and our experiments on real-world EHR data demonstrate that our proposed loss functions show benefits in improving the performance of strong baselines and even state-of-the-art models on benchmarking tasks for clinical risk predictions. Our loss functions work well with extremely imbalanced data which are common for clinical risk prediction problems. Our loss functions can be easily used to replace (binary or multi-label) cross-entropy loss adopted in existing clinical predictive models. The Pytorch code is released at \url{https://github.com/calvin-zcx/SCEHR}.

cs.LG↗

arXiv2021

Weakly Supervised Contrastive Learning

Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent achievement of contrastive learning. Most of the existing contrastive learning frameworks adopt the instance discrimination as the pretext task, which treating every single instance as a different class. However, such method will inevitably cause class collision problems, which hurts the quality of the learned representation. Motivated by this observation, we introduced a weakly supervised contrastive learning framework (WCL) to tackle this issue. Specifically, our proposed framework is based on two projection heads, one of which will perform the regular instance discrimination task. The other head will use a graph-based method to explore similar samples and generate a weak label, then perform a supervised contrastive learning task based on the weak label to pull the similar images closer. We further introduced a K-Nearest Neighbor based multi-crop strategy to expand the number of positive samples. Extensive experimental results demonstrate WCL improves the quality of self-supervised representations across different datasets. Notably, we get a new state-of-the-art result for semi-supervised learning. With only 1\% and 10\% labeled examples, WCL achieves 65\% and 72\% ImageNet Top-1 Accuracy using ResNet50, which is even higher than SimCLRv2 with ResNet101.

cs.CV↗

arXiv2021

HACCLE: Metaprogramming for Secure Multi-Party Computation -- Extended Version

Cryptographic techniques have the potential to enable distrusting parties to collaborate in fundamentally new ways, but their practical implementation poses numerous challenges. An important class of such cryptographic techniques is known as Secure Multi-Party Computation (MPC). Developing Secure MPC applications in realistic scenarios requires extensive knowledge spanning multiple areas of cryptography and systems. And while the steps to arrive at a solution for a particular application are often straightforward, it remains difficult to make the implementation efficient, and tedious to apply those same steps to a slightly different application from scratch. Hence, it is an important problem to design platforms for implementing Secure MPC applications with minimum effort and using techniques accessible to non-experts in cryptography. In this paper, we present the HACCLE (High Assurance Compositional Cryptography: Languages and Environments) toolchain, specifically targeted to MPC applications. HACCLE contains an embedded domain-specific language Harpoon, for software developers without cryptographic expertise to write MPC-based programs, and uses Lightweight Modular Staging (LMS) for code generation. Harpoon programs are compiled into acyclic circuits represented in HACCLE's Intermediate Representation (HIR) that serves as an abstraction over different cryptographic protocols such as secret sharing, homomorphic encryption, or garbled circuits. Implementations of different cryptographic protocols serve as different backends of our toolchain. The extensible design of HIR allows cryptographic experts to plug in new primitives and protocols to realize computation. And the use of standard metaprogramming techniques lowers the development effort significantly.

cs.PL↗

arXiv2021

Correcting the User Feedback-Loop Bias for Recommendation Systems

Selection bias is prevalent in the data for training and evaluating recommendation systems with explicit feedback. For example, users tend to rate items they like. However, when rating an item concerning a specific user, most of the recommendation algorithms tend to rely too much on his/her rating (feedback) history. This introduces implicit bias on the recommendation system, which is referred to as user feedback-loop bias in this paper. We propose a systematic and dynamic way to correct such bias and to obtain more diverse and objective recommendations by utilizing temporal rating information. Specifically, our method includes a deep-learning component to learn each user's dynamic rating history embedding for the estimation of the probability distribution of the items that the user rates sequentially. These estimated dynamic exposure probabilities are then used as propensity scores to train an inverse-propensity-scoring (IPS) rating predictor. We empirically validated the existence of such user feedback-loop bias in real world recommendation systems and compared the performance of our method with the baseline models that are either without de-biasing or with propensity scores estimated by other methods. The results show the superiority of our approach.

cs.IR↗

arXiv2021

Table-based Fact Verification with Salience-aware Learning

Tables provide valuable knowledge that can be used to verify textual statements. While a number of works have considered table-based fact verification, direct alignments of tabular data with tokens in textual statements are rarely available. Moreover, training a generalized fact verification model requires abundant labeled training data. In this paper, we propose a novel system to address these problems. Inspired by counterfactual causality, our system identifies token-level salience in the statement with probing-based salience estimation. Salience estimation allows enhanced learning of fact verification from two perspectives. From one perspective, our system conducts masked salient token prediction to enhance the model for alignment and reasoning between the table and the statement. From the other perspective, our system applies salience-aware data augmentation to generate a more diverse set of training instances by replacing non-salient terms. Experimental results on TabFact show the effective improvement by the proposed salience-aware learning techniques, leading to the new SOTA performance on the benchmark. Our code is publicly available at https://github.com/luka-group/Salience-aware-Learning .

cs.CL↗

arXiv2021

Convergence Rates of Attractive-Repulsive MCMC Algorithms

We consider MCMC algorithms for certain particle systems which include both attractive and repulsive forces, making their convergence analysis challenging. We prove that a version of these algorithms on a bounded state space is uniformly ergodic with an explicit quantitative convergence rate. We also prove that a version on an unbounded state-space is still geometrically ergodic, and then use the method of shift-coupling to obtain an explicit quantitative bound on its convergence rate.

math.PR↗

arXiv2021

The Coupling/Minorization/Drift Approach to Markov Chain Convergence Rates

This review paper provides an introduction of Markov chains and their convergence rates which is an important and interesting mathematical topic which also has important applications for very widely used Markov chain Monte Carlo (MCMC) algorithm. We first discuss eigenvalue analysis for Markov chains on finite state spaces. Then, using the coupling construction, we prove two quantitative bounds based on minorization condition and drift conditions, and provide descriptive and intuitive examples to showcase how these theorems can be implemented in practice. This paper is meant to provide a general overview of the subject and spark interest in new Markov chain research areas.

math.PR↗

arXiv2021

Event2Graph: Event-driven Bipartite Graph for Multivariate Time-series Anomaly Detection

Modeling inter-dependencies between time-series is the key to achieve high performance in anomaly detection for multivariate time-series data. The de-facto solution to model the dependencies is to feed the data into a recurrent neural network (RNN). However, the fully connected network structure underneath the RNN (either GRU or LSTM) assumes a static and complete dependency graph between time-series, which may not hold in many real-world applications. To alleviate this assumption, we propose a dynamic bipartite graph structure to encode the inter-dependencies between time-series. More concretely, we model time series as one type of nodes, and the time series segments (regarded as event) as another type of nodes, where the edge between two types of nodes describe a temporal pattern occurred on a specific time series at a certain time. Based on this design, relations between time series can be explicitly modelled via dynamic connections to event nodes, and the multivariate time-series anomaly detection problem can be formulated as a self-supervised, edge stream prediction problem in dynamic graphs. We conducted extensive experiments to demonstrate the effectiveness of the design.

cs.LG↗

arXiv2021

Explaining Algorithmic Fairness Through Fairness-Aware Causal Path Decomposition

Algorithmic fairness has aroused considerable interests in data mining and machine learning communities recently. So far the existing research has been mostly focusing on the development of quantitative metrics to measure algorithm disparities across different protected groups, and approaches for adjusting the algorithm output to reduce such disparities. In this paper, we propose to study the problem of identification of the source of model disparities. Unlike existing interpretation methods which typically learn feature importance, we consider the causal relationships among feature variables and propose a novel framework to decompose the disparity into the sum of contributions from fairness-aware causal paths, which are paths linking the sensitive attribute and the final predictions, on the graph. We also consider the scenario when the directions on certain edges within those paths cannot be determined. Our framework is also model agnostic and applicable to a variety of quantitative disparity measures. Empirical evaluations on both synthetic and real-world data sets are provided to show that our method can provide precise and comprehensive explanations to the model disparities.

cs.LG↗