arXiv subjects

Hongwei Wang

Publications and source records attributed to Hongwei Wang.

At least 127 records · Page 7Linked to original sources

arXiv2022

Supervised Contrastive Learning with Tree-Structured Parzen Estimator Bayesian Optimization for Imbalanced Tabular Data

Class imbalance has a detrimental effect on the predictive performance of most supervised learning algorithms as the imbalanced distribution can lead to a bias preferring the majority class. To solve this problem, we propose a Supervised Contrastive Learning (SCL) method with Tree-structured Parzen Estimator (TPE) technique for imbalanced tabular datasets. Contrastive learning (CL) can extract the information hidden in data even without labels and has shown some potential for imbalanced learning tasks. SCL further considers the label information based on CL, which also addresses the insufficient data augmentation techniques of tabular data. Therefore, in this work, we propose to use SCL to learn a discriminative representation of imbalanced tabular data. Additionally, the hyper-parameter temperature of SCL has a decisive influence on the performance and is difficult to tune. We introduce TPE, a well-known Bayesian optimization technique, to automatically select the best temperature. Experiments are conducted on both binary and multi-class imbalanced tabular datasets. As shown in the results obtained, TPE outperforms three other hyper-parameter optimization (HPO) methods such as grid search, random search, and genetic algorithm. More importantly, the proposed SCL-TPE method achieves much-improved performance compared with the state-of-the-art methods.

cs.LG↗

arXiv2022

Compressed CPD-Based Channel Estimation and Joint Beamforming for RIS-Assisted Millimeter Wave Communications

We consider the problem of channel estimation and joint active and passive beamforming for reconfigurable intelligent surface (RIS) assisted millimeter wave (mmWave) multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) systems. We show that, with a well-designed frame-based training protocol, the received pilot signal can be organized into a low-rank third-order tensor that admits a canonical polyadic decomposition (CPD). Based on this observation, we propose two CPD-based methods for estimating the cascade channels associated with different subcarriers. The proposed methods exploit the intrinsic low-rankness of the CPD formulation, which is a result of the sparse scattering characteristics of mmWave channels, and thus have the potential to achieve a significant training overhead reduction. Specifically, our analysis shows that the proposed methods have a sample complexity that scales quadratically with the sparsity of the cascade channel. Also, by utilizing the singular value decomposition-like structure of the effective channel, this paper develops a joint active and passive beamforming method based on the estimated cascade channels. Simulation results show that the proposed CPD-based channel estimation methods attain mean square errors that are close to the Cramer-Rao bound (CRB) and present a clear advantage over the compressed sensing-based method. In addition, the proposed joint beamforming method can effectively utilize the estimated channel parameters to achieve superior beamforming performance.

eess.SP↗

arXiv2022

Observing the Ping-pong Modality of Isospin Degree of Freedom in Cluster Emission from Heavy Ion Reactions

Two-body correlations of the isotope-resolved light and heavy clusters are measured in $^{86}$Kr+$^{\rm 208}$Pb reactions at 25 MeV/u. The yield and kinetic variables of the $A=3$ isobars, triton and $^3$He, are analyzed in coincidence with the heavy clusters of $7\le A \le 14$ emitted at the earlier chance. While the velocity spectra of both triton and $^3$He exhibit scaling behavior over the type of the heavy clusters, the yield ratios of ${\rm t/^3He}$ correlate reversely to the neutron-to-proton ratio $N/Z$ of the latter, showing the ping-pong modality of the $N/Z$ of emitted clusters. The commonality that the $N/Z$ of the residues keeps the initial system value is extended to the cluster emission in heavy ion reactions. The comparison of transport model calculations to the data is discussed.

nucl-ex↗

arXiv2022

Study of background from accidental coincidence signals in the PandaX-II experiment

The PandaX-II experiment employed a 580kg liquid xenon detector to search for the interactions between dark matter particles and the target xenon atoms. The accidental coincidences of isolated signals result in a dangerous background which mimic the signature of the dark matter. We performed a detailed study on the accidental coincidence background in PandaX-II, including the possible origin of the isolated signals, the background level and corresponding background suppression method. With a boosted-decision-tree algorithm, the accidental coincidence background is reduced by 70% in the dark matter signal region, thus the sensitivity of dark matter search at PandaX-II is improved.

hep-ex↗

arXiv2022

Schema-Guided Event Graph Completion

We tackle a new task, event graph completion, which aims to predict missing event nodes for event graphs. Existing link prediction or graph completion methods have difficulty dealing with event graphs because they are usually designed for a single large graph such as a social network or a knowledge graph, rather than multiple small dynamic event graphs. Moreover, they can only predict missing edges rather than missing nodes. In this work, we propose to utilize event schema, a template that describes the stereotypical structure of event graphs, to address the above issues. Our schema-guided event graph completion approach first maps an instance event graph to a subgraph of the schema graph by a heuristic subgraph matching algorithm. Then it predicts whether a candidate event node in the schema graph should be added to the instantiated schema subgraph by characterizing two types of local topology of the schema graph: neighbors of the candidate node and the subgraph, and paths that connect the candidate node and the subgraph. These two modules are later combined together for the final prediction. We also propose a self-supervised strategy to construct training samples, as well as an inference algorithm that is specifically designed to complete event graphs. Extensive experimental results on four datasets demonstrate that our proposed method achieves state-of-the-art performance, with 4.3% to 19.4% absolute F1 gains over the best baseline method on the four datasets.

cs.LG↗

arXiv2022

Spatial Channel Covariance Estimation and Two-Timescale Beamforming for IRS-Assisted Millimeter Wave Systems

We consider the problem of spatial channel covariance matrix (CCM) estimation for intelligent reflecting surface (IRS)-assisted millimeter wave (mmWave) communication systems. Spatial CCM is essential for two-timescale beamforming in IRS-assisted systems; however, estimating the spatial CCM is challenging due to the passive nature of reflecting elements and the large size of the CCM resulting from massive reflecting elements of the IRS. In this paper, we propose a CCM estimation method by exploiting the low-rankness as well as the positive semi-definite (PSD) 3-level Toeplitz structure of the CCM. Estimation of the CCM is formulated as a semidefinite programming (SDP) problem and an alternating direction method of multipliers (ADMM) algorithm is developed. Our analysis shows that the proposed method is theoretically guaranteed to attain a reliable CCM estimate with a sample complexity much smaller than the dimension of the CCM. Thus the proposed method can help achieve a significant training overhead reduction. Simulation results are presented to illustrate the effectiveness of our proposed method and the performance of two-timescale beamforming scheme based on the estimated CCM.

eess.SP↗

arXiv2022

Convert widespread paraelectric perovskite to ferroelectrics

While nature provides a plethora of perovskite materials, only a few exhibits large ferroelectricity and possibly multiferroicity. The majority of perovskite materials have the non-polar CaTiO$_3$(CTO)structure, limiting the scope of their applications. Based on effective Hamiltonian model as well as first-principles calculations, we propose a general thin-film design method to stabilize the functional BiFeO$_3$(BFO)-type structure, which is a common metastable structure in widespread CaTiO$_3$-type perovskite oxides. It is found that the improper antiferroelectricity in CTO-type perovskite and ferroelectricity in BFO-type perovskite have distinct dependences on mechanical and electric boundary conditions, both of which involve oxygen octahedral rotation and tilt. The above difference can be used to stabilize the highly polar BFO-type structure in many CTO-type perovskite materials.

cond-mat.mtrl-sci↗

arXiv2021

The Emission Order of Hydrogen Isotopes via Correlation Functions in 30 MeV/u Ar+Au Reactions

The intensity interferometry is applied as a chronometer of the particle emission of hydrogen isotopes from the intermediate velocity source formed in $^{40}$Ar+$^{197}$Au reactions at 30 MeV/u. The dynamic emission order of $τ_{\rm p}>τ_{\rm d}>τ_{\rm t}$ is evidenced via the correlation functions of nonidentical particle pairs. Assuming the similar source size, the same emission order is inferred from the correlation functions of identical particle pairs, where $τ_{\rm p} \approx 100 {\rm ~fm/c}$ is extracted by the fit of Koonin-Pratt equation to p-p correlation function. Transport model simulations demonstrate that the dynamic emission order of light charged particles depends on the stiffness of the nuclear symmetry energy.

nucl-ex↗

arXiv2021

A search for solar axions and anomalous neutrino magnetic moment with the complete PandaX-II data

We report a search for new physics signals using the low energy electron recoil events in the complete data set from PandaX-II, in light of the recent event excess reported by XENON1T. The data correspond to a total exposure of 100.7 ton-day with liquid xenon. With robust estimates of the dominant background spectra, we perform sensitive searches on solar axions and neutrinos with enhanced magnetic moment. We find that the axion-electron coupling $g_{Ae}<4.6\times 10^{-12}$ for an axion mass less than $\rm 0.1~keV/c^2$ and the neutrino magnetic moment $μ_ν<4.9\times 10^{-11}μ_{B}$ at 90% confidence level. The observed excess from XENON1T is within our experimental constraints.

hep-ex↗

arXiv2021

Constraining self-interacting dark matter with the full dataset of PandaX-II

Self-interacting Dark Matter (SIDM) is a leading candidate proposed to solve discrepancies between predictions of the prevailing cold dark matter theory and observations of galaxies. Many SIDM models predict the existence of a light force carrier that mediate strong dark matter self-interactions. If the mediator couples to the standard model particles, it could produce characteristic signals in dark matter direct detection experiments. We report searches for SIDM models with a light mediator using the full dataset of the PandaX-II experiment, based on a total exposure of 132 tonne-days. No significant excess over background is found, and our likelihood analysis leads to a strong upper limit on the dark matter-nucleon coupling strength. We further combine the PandaX-II constraints and those from observations of the light element abundances in the early universe, and show that direct detection and cosmological probes can provide complementary constraints on dark matter models with a light mediator.

hep-ex↗

arXiv2021

Horizontal Position Reconstruction in PandaX-II

Dual-phase noble-gas time projection chambers (TPCs) have improved the sensitivities for dark matter direct search in past decades. The capability of TPCs to reconstruct 3-D vertexes of keV scale recoilings is one of the most advantageous features. In this work, we develop two horizontal position reconstruction algorithms for the PandaX-II dark matter search experiment using the dual-phase liquid xenon TPC. Both algorithms are optimized by the $^{83m}$Kr calibration events and use photon distribution of ionization signals among photomultiplier tubes to infer the positions. According to the events coming from the gate electrode, the uncertainties in the horizontal positions are 3.4 mm (3.9 mm) in the analytical (simulation-based) algorithm for an ionization signal with several thousand photon electrons in the center of the TPC

physics.ins-det↗

arXiv2021

Properties of the fast fission and the coincident emissions of light charged particles in $^{40}$Ar + $^{197}$Au reactions at 30 MeV/u

The experiment of Ar+Au reactions at 30 MeV/u have been performed using the Compact Spectrometer for Heavy IoN Experiments (CSHINE) in phase I. The light-charged particles are measured by the silicon stripe telescopes in coincidence with the fission fragments recorded by the parallel plate avalanche counters. The distribution properties of the azimuth difference $Δϕ$ and the time-of-flight difference $ΔTOF$ of the fission fragments are presented varying the folding angles which represents the linear momentum transfer from the projectile to the reaction system. The relative abundance of the light charged particles in the fission events to the inclusive events is compared as a function of the laboratory angle $θ_{\rm lab}$ ranging from $18^\circ$ to $60^\circ$ in various folding angle windows. The angular evolution of the yield ratios of p/d and t/d in coincidence with fission fragments is investigated. In a relative comparison, tritons are more abundantly emitted at small angles, while protons are more abundant at large angles. The angular evolution of the neutron richness of the light-charged particles is consistent with the results obtained in previous inclusive experiments.

nucl-ex↗

arXiv2021

Chemical-Reaction-Aware Molecule Representation Learning

Molecule representation learning (MRL) methods aim to embed molecules into a real vector space. However, existing SMILES-based (Simplified Molecular-Input Line-Entry System) or GNN-based (Graph Neural Networks) MRL methods either take SMILES strings as input that have difficulty in encoding molecule structure information, or over-emphasize the importance of GNN architectures but neglect their generalization ability. Here we propose using chemical reactions to assist learning molecule representation. The key idea of our approach is to preserve the equivalence of molecules with respect to chemical reactions in the embedding space, i.e., forcing the sum of reactant embeddings and the sum of product embeddings to be equal for each chemical equation. This constraint is proven effective to 1) keep the embedding space well-organized and 2) improve the generalization ability of molecule embeddings. Moreover, our model can use any GNN as the molecule encoder and is thus agnostic to GNN architectures. Experimental results demonstrate that our method achieves state-of-the-art performance in a variety of downstream tasks, e.g., 17.4% absolute Hit@1 gain in chemical reaction prediction, 2.3% absolute AUC gain in molecule property prediction, and 18.5% relative RMSE gain in graph-edit-distance prediction, respectively, over the best baseline method. The code is available at https://github.com/hwwang55/MolR.

cs.LG↗

arXiv2021

An efficient algorithm for simulating ensembles of parameterized MHD flow problems

In this paper, we propose, analyze, and test an efficient algorithm for computing ensemble average of incompressible magnetohydrodynamics (MHD) flows, where instances/members correspond to varying kinematic viscosity, magnetic diffusivity, body forces, and initial conditions. The algorithm is decoupled in Elsässer variables and permits a shared coefficient matrix for all members at each time-step. Thus, the algorithm is much more computationally efficient than separately computing simulations for each member using usual MHD algorithms. We prove the proposed algorithm is unconditionally stable and convergent. Several numerical tests are given to support the predicted convergence rates. Finally, we test the proposed scheme and observe how the physical behavior changes as the coupling number increases in a lid-driven cavity problem with mean Reynolds number $Re\approx 15000$, and as the deviation of uncertainties in the initial and boundary conditions increases in a channel flow past a step problem.

math.NA↗

arXiv2021

Multi-Agent Imitation Learning with Copulas

Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions, which is essential for understanding physical, social, and team-play systems. However, most existing works on modeling multi-agent interactions typically assume that agents make independent decisions based on their observations, ignoring the complex dependence among agents. In this paper, we propose to use copula, a powerful statistical tool for capturing dependence among random variables, to explicitly model the correlation and coordination in multi-agent systems. Our proposed model is able to separately learn marginals that capture the local behavioral patterns of each individual agent, as well as a copula function that solely and fully captures the dependence structure among agents. Extensive experiments on synthetic and real-world datasets show that our model outperforms state-of-the-art baselines across various scenarios in the action prediction task, and is able to generate new trajectories close to expert demonstrations.

cs.LG↗

arXiv2021

Searching for Dark Matter Particles with Compton Scattering Approach

The dark matter puzzle is one of the most important fundamental physics questions in 21 century. There is no doubt that solving the puzzle will be a new milestone for human beings in the way of deeper understanding the mother nature. Here we propose to use the Shanghai laser electron gamma source (SLEGS) to search for dark matter candidates particles, including dark pseudo scalar particles, dark scalar particles, and dark photons. Our simulations show that electron facilities like SLEGS with some upgrading could be competitive platforms in searching for light dark matter particles with mass under tens of keV.

hep-ex↗

arXiv2021

Relational Message Passing for Knowledge Graph Completion

Knowledge graph completion aims to predict missing relations between entities in a knowledge graph. In this work, we propose a relational message passing method for knowledge graph completion. Different from existing embedding-based methods, relational message passing only considers edge features (i.e., relation types) without entity IDs in the knowledge graph, and passes relational messages among edges iteratively to aggregate neighborhood information. Specifically, two kinds of neighborhood topology are modeled for a given entity pair under the relational message passing framework: (1) Relational context, which captures the relation types of edges adjacent to the given entity pair; (2) Relational paths, which characterize the relative position between the given two entities in the knowledge graph. The two message passing modules are combined together for relation prediction. Experimental results on knowledge graph benchmarks as well as our newly proposed dataset show that, our method PathCon outperforms state-of-the-art knowledge graph completion methods by a large margin. PathCon is also shown applicable to inductive settings where entities are not seen in training stage, and it is able to provide interpretable explanations for the predicted results. The code and all datasets are available at https://github.com/hwwang55/PathCon.

cs.LG↗

arXiv2021

RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation

Existing online multiple object tracking (MOT) algorithms often consist of two subtasks, detection and re-identification (ReID). In order to enhance the inference speed and reduce the complexity, current methods commonly integrate these double subtasks into a unified framework. Nevertheless, detection and ReID demand diverse features. This issue would result in an optimization contradiction during the training procedure. With the target of alleviating this contradiction, we devise a module named Global Context Disentangling (GCD) that decouples the learned representation into detection-specific and ReID-specific embeddings. As such, this module provides an implicit manner to balance the different requirements of these two subtasks. Moreover, we observe that preceding MOT methods typically leverage local information to associate the detected targets and neglect to consider the global semantic relation. To resolve this restriction, we develop a module, referred to as Guided Transformer Encoder (GTE), by combining the powerful reasoning ability of Transformer encoder and deformable attention. Unlike previous works, GTE avoids analyzing all the pixels and only attends to capture the relation between query nodes and a few self-adaptively selected key samples. Therefore, it is computationally efficient. Extensive experiments have been conducted on the MOT16, MOT17 and MOT20 benchmarks to demonstrate the superiority of the proposed MOT framework, namely RelationTrack. The experimental results indicate that RelationTrack has surpassed preceding methods significantly and established a new state-of-the-art performance, e.g., IDF1 of 70.5% and MOTA of 67.2% on MOT20.

cs.CV↗