arXiv subjects

Wei Wei

Publications and source records attributed to Wei Wei.

At least 343 records · Page 19Linked to original sources

arXiv2022

CmnRec: Sequential Recommendations with Chunk-accelerated Memory Network

Recently, Memory-based Neural Recommenders (MNR) have demonstrated superior predictive accuracy in the task of sequential recommendations, particularly for modeling long-term item dependencies. However, typical MNR requires complex memory access operations, i.e., both writing and reading via a controller (e.g., RNN) at every time step. Those frequent operations will dramatically increase the network training time, resulting in the difficulty in being deployed on industrial-scale recommender systems. In this paper, we present a novel general Chunk framework to accelerate MNR significantly. Specifically, our framework divides proximal information units into chunks, and performs memory access at certain time steps, whereby the number of memory operations can be greatly reduced. We investigate two ways to implement effective chunking, i.e., PEriodic Chunk (PEC) and Time-Sensitive Chunk (TSC), to preserve and recover important recurrent signals in the sequence. Since chunk-accelerated MNR models take into account more proximal information units than that from a single timestep, it can remove the influence of noise in the item sequence to a large extent, and thus improve the stability of MNR. In this way, the proposed chunk mechanism can lead to not only faster training and prediction, but even slightly better results. The experimental results on three real-world datasets (weishi, ml-10M and ml-latest) show that our chunk framework notably reduces the running time (e.g., with up to 7x for training & 10x for inference on ml-latest) of MNR, and meantime achieves competitive performance.

cs.IR↗

arXiv2022

A $σ_{2}$ Penrose inequality for conformal asymptotically hyperbolic 4-discs

In this paper, we consider conformal metrics on a unit 4-disc with an asymptotically hyperbolic end and possible isolated conic singularities. We define a mass term of the AH end. If the $σ_{2}$ curvature has lower bound $σ_{2}\geq\frac{3}{2}$, we prove a Penrose type inequality relating the mass and contributions from singularities. We also classify sharp cases, which is the standard hyperbolic 4-space $\mathbb{H}^{4}$ when no singularity occurs. It is worth noting that our curvature condition implies non-positive energy density.

math.DG↗

arXiv2022

Optimal configuration of cooperative stationary and mobile energy storage considering ambient temperature: A case for Winter Olympic Game

The international mega-event, such as the Winter Olympic Game, has been considered as one of the most carbon intensive activities worldwide. The commitment of fully renewable energy accommodation and utilization while ensuring the extreme high reliability has brought significant challenges on system operation due to the stochastic nature of the renewables. The battery energy storage system (BESS) composed of stationary energy storage system (SESS) and shared mobile energy storage system (MESS) can be utilized to meet the requirements of short-term load surges, renewable accommodation and emergency power supply for important loads during the mega-event. The BESS can continue to serve the venues electricity consumption to satisfy the carbon neutrality after the event. On the other hand, the low ambient temperature of Winter Olympic game has significant impact on BESSs degradation and performance which need to be integrated to the charging and discharging model of BESS. To this end, a joint two-stage optimal configuration method considering the ambient temperature of SESS and MESS has been developed to support the mega-event carbon neutrality, to reduce redundant BESS capacity allocation and improve the system life cycle cost-benefit. Simulation results have demonstrated the rationality and effectiveness of the collaborative operation of SESS and the MESS under various scenarios.

eess.SY↗

arXiv2022

Contrastive Meta Learning with Behavior Multiplicity for Recommendation

A well-informed recommendation framework could not only help users identify their interested items, but also benefit the revenue of various online platforms (e.g., e-commerce, social media). Traditional recommendation models usually assume that only a single type of interaction exists between user and item, and fail to model the multiplex user-item relationships from multi-typed user behavior data, such as page view, add-to-favourite and purchase. While some recent studies propose to capture the dependencies across different types of behaviors, two important challenges have been less explored: i) Dealing with the sparse supervision signal under target behaviors (e.g., purchase). ii) Capturing the personalized multi-behavior patterns with customized dependency modeling. To tackle the above challenges, we devise a new model CML, Contrastive Meta Learning (CML), to maintain dedicated cross-type behavior dependency for different users. In particular, we propose a multi-behavior contrastive learning framework to distill transferable knowledge across different types of behaviors via the constructed contrastive loss. In addition, to capture the diverse multi-behavior patterns, we design a contrastive meta network to encode the customized behavior heterogeneity for different users. Extensive experiments on three real-world datasets indicate that our method consistently outperforms various state-of-the-art recommendation methods. Our empirical studies further suggest that the contrastive meta learning paradigm offers great potential for capturing the behavior multiplicity in recommendation. We release our model implementation at: https://github.com/weiwei1206/CML.git.

cs.IR↗

arXiv2022

Underwater Differential Game: Finite-Time Target Hunting Task with Communication Delay

This work considers designing an unmanned target hunting system for a swarm of unmanned underwater vehicles (UUVs) to hunt a target with high maneuverability. Differential game theory is used to analyze combat policies of UUVs and the target within finite time. The challenge lies in UUVs must conduct their control policies in consideration of not only the consistency of the hunting team but also escaping behaviors of the target. To obtain stable feedback control policies satisfying Nash equilibrium, we construct the Hamiltonian function with Leibniz's formula. For further taken underwater disturbances and communication delay into consideration, modified deep reinforcement learning (DRL) is provided to investigate the underwater target hunting task in an unknown dynamic environment. Simulations show that underwater disturbances have a large impact on the system considering communication delay. Moreover, consistency tests show that UUVs perform better consistency with a relatively small range of disturbances.

eess.SY↗

arXiv2022

Meta-CPR: Generalize to Unseen Large Number of Agents with Communication Pattern Recognition Module

Designing an effective communication mechanism among agents in reinforcement learning has been a challenging task, especially for real-world applications. The number of agents can grow or an environment sometimes needs to interact with a changing number of agents in real-world scenarios. To this end, a multi-agent framework needs to handle various scenarios of agents, in terms of both scales and dynamics, for being practical to real-world applications. We formulate the multi-agent environment with a different number of agents as a multi-tasking problem and propose a meta reinforcement learning (meta-RL) framework to tackle this problem. The proposed framework employs a meta-learned Communication Pattern Recognition (CPR) module to identify communication behavior and extract information that facilitates the training process. Experimental results are poised to demonstrate that the proposed framework (a) generalizes to an unseen larger number of agents and (b) allows the number of agents to change between episodes. The ablation study is also provided to reason the proposed CPR design and show such design is effective.

cs.LG↗

arXiv2022

Credit Valuation Adjustment with Replacement Closeout: Theory and Algorithms

The replacement closeout convention has drawn more and more attention since the 2008 financial crisis. Compared with the conventional risk-free closeout, the replacement closeout convention incorporates the creditworthiness of the counterparty and thus providing a more accurate estimate of the Mark-to-market value of a financial claim. In contrast to the risk-free closeout, the replacement closeout renders a nonlinear valuation system, which constitutes the major difficulty in the valuation of the counterparty credit risk. In this paper, we show how to address the nonlinearity attributed to the replacement closeout in the theoretical and computational analysis. In the theoretical part, we prove the unique solvability of the nonlinear valuation system and study the impact of the replacement closeout on the credit valuation adjustment. In the computational part, we propose a neural network-based algorithm for solving the (high dimensional) nonlinear valuation system and effectively alleviating the curse of dimensionality. We numerically compare the computational cost for the valuations with risk-free and replacement closeouts. The numerical tests confirm both the accuracy and the computational efficiency of our proposed algorithm for the valuation of the replacement closeout.

q-fin.MF↗

arXiv2022

Almost sharp Sobolev trace inequalities in the unit ball under constraints

We establish three families of Sobolev trace inequalities of orders two and four in the unit ball under higher order moments constraint, and are able to construct \emph{smooth} test functions to show all such inequalities are \emph{almost optimal}. Some distinct feature in \emph{almost sharpness} examples between the fourth order and second order Sobolev trace inequalities is discovered. This has been neglected in higher order Sobolev inequality case in \cite{Hang}. As a byproduct, the method of our construction can be used to show the sharpness of the generalized Lebedev-Milin inequality under constraints.

math.DG↗

arXiv2021

Protonation-induced discrete superconducting phases in bulk FeSe single crystals

The superconducting transition temperature, $T_{\rm{c}}$, of FeSe can be significantly enhanced several-fold by applying pressure, electron doping, intercalating spacing layer, and reducing dimensionality. Various ordered electronic phases, such as nematicity and spin density waves, have also been observed accompanying high-$T_{\rm{c}}$ superconductivity. Investigation on the evolution of the electronic structure with $T_{\rm{c}}$ is essential to understanding electronic behavior and high-$T_{\rm{c}}$ superconductivity in FeSe and its derived superconductors. In this report, we have found a series of discrete superconducting phases, with a maximum $T_{\rm{c}}$ up to 44 K, in H$^+$-intercalated FeSe single crystals using an ionic liquid gating method. Accompanied with the increase of $T_{\rm{c}}$, suppression of the nematic phase and evolution from non-Fermi-liquid to Fermi-liquid behavior was observed. An abrupt change in the Fermi surface topology was proposed to explain the discrete superconducting phases. A band structure that favors the high-$T_{\rm{c}}$ superconducting phase was also revealed.

cond-mat.supr-con↗

arXiv2021

RATE: Overcoming Noise and Sparsity of Textual Features in Real-Time Location Estimation

Real-time location inference of social media users is the fundamental of some spatial applications such as localized search and event detection. While tweet text is the most commonly used feature in location estimation, most of the prior works suffer from either the noise or the sparsity of textual features. In this paper, we aim to tackle these two problems. We use topic modeling as a building block to characterize the geographic topic variation and lexical variation so that "one-hot" encoding vectors will no longer be directly used. We also incorporate other features which can be extracted through the Twitter streaming API to overcome the noise problem. Experimental results show that our RATE algorithm outperforms several benchmark methods, both in the precision of region classification and the mean distance error of latitude and longitude regression.

cs.CL↗

arXiv2021

Deep Learning with Quantized Neural Networks for Gravitational Wave Forecasting of Eccentric Compact Binary Coalescence

We present the first application of deep learning forecasting for binary neutron stars, neutron star - black hole systems, and binary black hole mergers that span an eccentricity range e <= 0.9. We train neural networks that describe these astrophysical populations, and then test their performance by injecting simulated eccentric signals in advanced LIGO noise available at the \texttt{Gravitational Wave Open Science Center} to: 1) quantify how fast neural networks identify these signals before the binary components merge; 2) quantify how accurately neural networks estimate the time to merger once gravitational waves are identified; and 3) estimate the time-dependent sky localization of these events from early detection to merger. Our findings show that deep learning can identify eccentric signals from a few seconds (for binary black holes) up to tens of seconds (for binary neutron stars) prior to merger. A quantized version of our neural networks achieves 4x reduction in model size, and up to 2.5x inference speed up. These novel algorithms may be used to facilitate time-sensitive multi-messenger astrophysics observations of compact binaries in dense stellar environments.

gr-qc↗

arXiv2021

Position-Aware Self-Attention based Neural Sequence Labeling

Sequence labeling is a fundamental task in natural language processing and has been widely studied. Recently, RNN-based sequence labeling models have increasingly gained attentions. Despite superior performance achieved by learning the long short-term (i.e., successive) dependencies, the way of sequentially processing inputs might limit the ability to capture the non-continuous relations over tokens within a sentence. To tackle the problem, we focus on how to effectively model successive and discrete dependencies of each token for enhancing the sequence labeling performance. Specifically, we propose an innovative attention-based model (called position-aware selfattention, i.e., PSA) as well as a well-designed self-attentional context fusion layer within a neural network architecture, to explore the positional information of an input sequence for capturing the latent relations among tokens. Extensive experiments on three classical tasks in sequence labeling domain, i.e., partof-speech (POS) tagging, named entity recognition (NER) and phrase chunking, demonstrate our proposed model outperforms the state-of-the-arts without any external knowledge, in terms of various metrics.

cs.CL↗

arXiv2021

On the Time-Inconsistent Deterministic Linear-Quadratic Control

A fundamental theory of deterministic linear-quadratic (LQ) control is the equivalent relationship between control problems, two-point boundary value problems and Riccati equations. In this paper, we extend the equivalence to a general time-inconsistent deterministic LQ problem, where the inconsistency arises from non-exponential discount functions. By studying the solvability of the Riccati equation, we show the existence and uniqueness of the linear equilibrium for the time-inconsistent LQ problem.

q-fin.MF↗

arXiv2021

A Region-based Collaborative Management Scheme for Dynamic Clustering in Green VANET

Green Vehicular Ad-hoc Network (VANET) is a newly-emerged research area which focuses on reducing harmful impacts of vehicular communication equipments on the natural environment. Recent studies have shown that grouping vehicles into clusters for green communications in VANETs can significantly improve networking efficiency and reduce infrastructure costs. As a dynamic network system, maintaining the network connectivity and reducing the communication overlap are two critical challenges for green VANET clustering. However, most existing work studies connectivity and overlap separately, lacking a deep understanding of the relationship between them. To address this issue, we present a comprehensive analysis that jointly considers the two critical factors in one model. Specifically, we first design a state resemblance prediction (SRP) model based on the historical trajectory feature relevance between vehicles; Combined with the SRP model, we propose the region-based collaborative management scheme (RCMS) to establish the dynamic clustering; Lastly, we take extensive experiments to verify the region-based collaborative management scheme for dynamic clustering. The results demonstrate that the proposed clustering algorithm can achieve high networking efficiency and better communication stability.

cs.NI↗

arXiv2021

Approaching the Transient Stability Boundary of a Power System: Theory and Applications

Estimating the stability boundary is a fundamental and challenging problem in transient stability studies. It is known that a proper level set of a Lyapunov function or an energy function can provide an inner approximation of the stability boundary, and the estimation can be expanded by trajectory reversing methods. In this paper, we streamline the theoretical foundation of the expansion methodology, and generalize it by relaxing the request that the initial guess should be a subset of the stability region. We investigate topological characteristics of the expanded boundary, showing how an initial guess can approach the exact stability boundary locally or globally. We apply the theory to transient stability assessment, and propose expansion algorithms to improve the well-known Potential Energy Boundary Surface (PEBS) and Boundary of stability region based Controlling Unstable equilibrium point (BCU) methods. Case studies on the IEEE 39-bus system well verify our results and demonstrate that estimations of the stability boundary and the critical clearing time can be significantly improved with modest computational cost.

eess.SY↗

arXiv2021

Geometry-Entangled Visual Semantic Transformer for Image Captioning

Recent advancements of image captioning have featured Visual-Semantic Fusion or Geometry-Aid attention refinement. However, those fusion-based models, they are still criticized for the lack of geometry information for inter and intra attention refinement. On the other side, models based on Geometry-Aid attention still suffer from the modality gap between visual and semantic information. In this paper, we introduce a novel Geometry-Entangled Visual Semantic Transformer (GEVST) network to realize the complementary advantages of Visual-Semantic Fusion and Geometry-Aid attention refinement. Concretely, a Dense-Cap model proposes some dense captions with corresponding geometry information at first. Then, to empower GEVST with the ability to bridge the modality gap among visual and semantic information, we build four parallel transformer encoders VV(Pure Visual), VS(Semantic fused to Visual), SV(Visual fused to Semantic), SS(Pure Semantic) for final caption generation. Both visual and semantic geometry features are used in the Fusion module and also the Self-Attention module for better attention measurement. To validate our model, we conduct extensive experiments on the MS-COCO dataset, the experimental results show that our GEVST model can obtain promising performance gains.

cs.CV↗

arXiv2021

An Improved Surrogate Method for Solving the Energy Storage Optimal Bidding Problem

Energy storage is expected to play an increasingly important role in mitigating variations that come along with the growing penetration of renewable energy. In this paper, we study the optimal bidding of an energy storage unit in a semi-centralized market. The energy storage unit offers its available storage capacity and maximum charging/discharging rate to the operator; then the operator clears the real-time market by minimizing the total cost. The energy storage unit is paid/charged at locational marginal price (LMP). The problem casts down to a bilevel optimization problem with a mixed-integer lower-level. An improved surrogate-based method with the combined spatial-temporal entropy term is developed to solve this problem. Numerical examples demonstrate the scalability, efficiency, and accuracy of the proposed method.

math.OC↗

arXiv2021

Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach

Reliable automatic evaluation of dialogue systems under an interactive environment has long been overdue. An ideal environment for evaluating dialog systems, also known as the Turing test, needs to involve human interaction, which is usually not affordable for large-scale experiments. Though researchers have attempted to use metrics (e.g., perplexity, BLEU) in language generation tasks or some model-based reinforcement learning methods (e.g., self-play evaluation) for automatic evaluation, these methods only show a very weak correlation with the actual human evaluation in practice. To bridge such a gap, we propose a new framework named ENIGMA for estimating human evaluation scores based on recent advances of off-policy evaluation in reinforcement learning. ENIGMA only requires a handful of pre-collected experience data, and therefore does not involve human interaction with the target policy during the evaluation, making automatic evaluations feasible. More importantly, ENIGMA is model-free and agnostic to the behavior policies for collecting the experience data (see details in Section 2), which significantly alleviates the technical difficulties of modeling complex dialogue environments and human behaviors. Our experiments show that ENIGMA significantly outperforms existing methods in terms of correlation with human evaluation scores.

cs.CL↗