arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 1,243 records · Page 69Linked to original sources

arXiv2022

FIS-GAN: GAN with Flow-based Importance Sampling

Generative Adversarial Networks (GAN) training process, in most cases, apply Uniform or Gaussian sampling methods in the latent space, which probably spends most of the computation on examples that can be properly handled and easy to generate. Theoretically, importance sampling speeds up stochastic optimization in supervised learning by prioritizing training examples. In this paper, we explore the possibility of adapting importance sampling into adversarial learning. We use importance sampling to replace Uniform and Gaussian sampling methods in the latent space and employ normalizing flow to approximate latent space posterior distribution by density estimation. Empirically, results on MNIST and Fashion-MNIST demonstrate that our method significantly accelerates GAN's optimization while retaining visual fidelity in generated samples.

cs.LG↗

arXiv2022

First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting

Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years. In addition to learning attention in time domain, recent works also explore learning attention in frequency domains (e.g., Fourier domain, wavelet domain), given that seasonal patterns can be better captured in these domains. In this work, we seek to understand the relationships between attention models in different time and frequency domains. Theoretically, we show that attention models in different domains are equivalent under linear conditions (i.e., linear kernel to attention scores). Empirically, we analyze how attention models of different domains show different behaviors through various synthetic experiments with seasonality, trend and noise, with emphasis on the role of softmax operation therein. Both these theoretical and empirical analyses motivate us to propose a new method: TDformer (Trend Decomposition Transformer), that first applies seasonal-trend decomposition, and then additively combines an MLP which predicts the trend component with Fourier attention which predicts the seasonal component to obtain the final prediction. Extensive experiments on benchmark time-series forecasting datasets demonstrate that TDformer achieves state-of-the-art performance against existing attention-based models.

cs.LG↗

arXiv2022

Proximal Policy Optimization Based Reinforcement Learning for Joint Bidding in Energy and Frequency Regulation Markets

Driven by the global decarbonization effort, the rapid integration of renewable energy into the conventional electricity grid presents new challenges and opportunities for the battery energy storage system (BESS) participating in the energy market. Energy arbitrage can be a significant source of revenue for the BESS due to the increasing price volatility in the spot market caused by the mismatch between renewable generation and electricity demand. In addition, the Frequency Control Ancillary Services (FCAS) markets established to stabilize the grid can offer higher returns for the BESS due to their capability to respond within milliseconds. Therefore, it is crucial for the BESS to carefully decide how much capacity to assign to each market to maximize the total profit under uncertain market conditions. This paper formulates the bidding problem of the BESS as a Markov Decision Process, which enables the BESS to participate in both the spot market and the FCAS market to maximize profit. Then, Proximal Policy Optimization, a model-free deep reinforcement learning algorithm, is employed to learn the optimal bidding strategy from the dynamic environment of the energy market under a continuous bidding scale. The proposed model is trained and validated using real-world historical data of the Australian National Electricity Market. The results demonstrate that our developed joint bidding strategy in both markets is significantly profitable compared to individual markets.

eess.SY↗

arXiv2022

Model-Free Approach to Fair Solar PV Curtailment Using Reinforcement Learning

The rapid adoption of residential solar photovoltaics (PV) has resulted in regular overvoltage events, due to correlated reverse power flows. Currently, PV inverters prevent damage to electronics by curtailing energy production in response to overvoltage. However, this disproportionately affects households at the far end of the feeder, leading to an unfair allocation of the potential value of energy produced. Globally optimizing for fair curtailment requires accurate feeder parameters, which are often unknown. This paper investigates reinforcement learning, which gradually optimizes a fair PV curtailment strategy by interacting with the system. We evaluate six fairness metrics on how well they can be learned compared to an optimal solution oracle. We show that all definitions permit efficient learning, suggesting that reinforcement learning is a promising approach to achieving both safe and fair PV coordination.

eess.SY↗

arXiv2022

Complete cavity map of the C. elegans connectome

Network structure or topology is the basis for understanding complex systems. Recently, higher-order structures have been considered as a new research direction that can provide new perspectives and phenomena. However, most existing studies have focused on simple 1-cycles and triangles, and few have explored the higher-order and non-trivial cycles. The current study focused on the cavity, which is a non-trivial cycle. We proposed a method to compute cavities with different orders based on pruning in the boundary matrix and calculated all cavities of the neural network of Caenorhabditis elegans (\emph{C. elegans}) neural network. This study reports for the first time a complete cavity map of C. elegans neural network, developing a new method for mining higher-order structures that can be applied by researchers in neuroscience, network science and other interdisciplinary fields to explore higher-order structural markers of complex systems.

q-bio.NC↗

arXiv2022

PoissonMat: Remodeling Matrix Factorization using Poisson Distribution and Solving the Cold Start Problem without Input Data

Matrix Factorization is one of the most successful recommender system techniques over the past decade. However, the classic probabilistic theory framework for matrix factorization is modeled using normal distributions. To find better probabilistic models, algorithms such as RankMat, ZeroMat and DotMat have been invented in recent years. In this paper, we model the user rating behavior in recommender system as a Poisson process, and design an algorithm that relies on no input data to solve the recommendation problem and the cold start issue at the same time. We prove the superiority of our algorithm in comparison with matrix factorization, random placement, Zipf placement, ZeroMat, DotMat, etc.

cs.IR↗

arXiv2022

Pareto Pairwise Ranking for Fairness Enhancement of Recommender Systems

Learning to rank is an effective recommendation approach since its introduction around 2010. Famous algorithms such as Bayesian Personalized Ranking and Collaborative Less is More Filtering have left deep impact in both academia and industry. However, most learning to rank approaches focus on improving technical accuracy metrics such as AUC, MRR and NDCG. Other evaluation metrics of recommender systems like fairness have been largely overlooked until in recent years. In this paper, we propose a new learning to rank algorithm named Pareto Pairwise Ranking. We are inspired by the idea of Bayesian Personalized Ranking and power law distribution. We show that our algorithm is competitive with other algorithms when evaluated on technical accuracy metrics. What is more important, in our experiment section we demonstrate that Pareto Pairwise Ranking is the most fair algorithm in comparison with 9 other contemporary algorithms.

cs.IR↗

arXiv2022

Direct van der Waals simulation (DVS) of phase-transforming fluids

We present the method of Direct van der Waals simulation (DVS) to study computationally flows with liquid-vapor phase transformations. Our approach is based on a novel discretization of the Navier-Stokes-Korteweg equations, that couple flow dynamics with van der Waals' non-equilibrium thermodynamic theory of phase transformations, and opens an opportunity for first-principles simulation of a wide range of boiling and cavitating flows. The proposed algorithm enables unprecedented simulations of the Navier-Stokes-Korteweg equations involving cavitating flows at strongly under-critical conditions and $\mathcal{O}(10^5)$ Reynolds number. The proposed technique provides a pathway for fundamental understanding of phase-transforming flows with multiple applications in science, engineering, and medicine.

physics.flu-dyn↗

arXiv2022

Federated Unlearning for On-Device Recommendation

The increasing data privacy concerns in recommendation systems have made federated recommendations (FedRecs) attract more and more attention. Existing FedRecs mainly focus on how to effectively and securely learn personal interests and preferences from their on-device interaction data. Still, none of them considers how to efficiently erase a user's contribution to the federated training process. We argue that such a dual setting is necessary. First, from the privacy protection perspective, ``the right to be forgotten'' requires that users have the right to withdraw their data contributions. Without the reversible ability, FedRecs risk breaking data protection regulations. On the other hand, enabling a FedRec to forget specific users can improve its robustness and resistance to malicious clients' attacks. To support user unlearning in FedRecs, we propose an efficient unlearning method FRU (Federated Recommendation Unlearning), inspired by the log-based rollback mechanism of transactions in database management systems. It removes a user's contribution by rolling back and calibrating the historical parameter updates and then uses these updates to speed up federated recommender reconstruction. However, storing all historical parameter updates on resource-constrained personal devices is challenging and even infeasible. In light of this challenge, we propose a small-sized negative sampling method to reduce the number of item embedding updates and an importance-based update selection mechanism to store only important model updates. To evaluate the effectiveness of FRU, we propose an attack method to disturb FedRecs via a group of compromised users and use FRU to recover recommenders by eliminating these users' influence. Finally, we conduct experiments on two real-world recommendation datasets with two widely used FedRecs to show the efficiency and effectiveness of our proposed approaches.

cs.IR↗

arXiv2022

AL-iGAN: An Active Learning Framework for Tunnel Geological Reconstruction Based on TBM Operational Data

In tunnel boring machine (TBM) underground projects, an accurate description of the rock-soil types distributed in the tunnel can decrease the construction risk ({\it e.g.} surface settlement and landslide) and improve the efficiency of construction. In this paper, we propose an active learning framework, called AL-iGAN, for tunnel geological reconstruction based on TBM operational data. This framework contains two main parts: one is the usage of active learning techniques for recommending new drilling locations to label the TBM operational data and then to form new training samples; and the other is an incremental generative adversarial network for geological reconstruction (iGAN-GR), whose weights can be incrementally updated to improve the reconstruction performance by using the new samples. The numerical experiment validate the effectiveness of the proposed framework as well.

cs.LG↗

arXiv2022

Visual Prompt Tuning for Test-time Domain Adaptation

Models should be able to adapt to unseen data during test-time to avoid performance drops caused by inevitable distribution shifts in real-world deployment scenarios. In this work, we tackle the practical yet challenging test-time adaptation (TTA) problem, where a model adapts to the target domain without accessing the source data. We propose a simple recipe called \textit{Data-efficient Prompt Tuning} (DePT) with two key ingredients. First, DePT plugs visual prompts into the vision Transformer and only tunes these source-initialized prompts during adaptation. We find such parameter-efficient finetuning can efficiently adapt the model representation to the target domain without overfitting to the noise in the learning objective. Second, DePT bootstraps the source representation to the target domain by memory bank-based online pseudo-labeling. A hierarchical self-supervised regularization specially designed for prompts is jointly optimized to alleviate error accumulation during self-training. With much fewer tunable parameters, DePT demonstrates not only state-of-the-art performance on major adaptation benchmarks VisDA-C, ImageNet-C, and DomainNet-126, but also superior data efficiency, i.e., adaptation with only 1\% or 10\% data without much performance degradation compared to 100\% data. In addition, DePT is also versatile to be extended to online or multi-source TTA settings.

cs.CV↗

arXiv2022

Efficient a Posteriori Error Control of a Consistent Atomistic/Continuum Coupling Method for Two Dimensional Crystalline Defects

Adaptive atomistic/continuum (a/c) coupling method is an important method for the simulation of material and atomistic systems with defects to achieve the balance of accuracy and efficiency. Residual based a posteriori error estimator is often employed in the adaptive algorithm to provide an estimate of the error of the strain committed by applying the continuum approximation for the atomistic system and the finite element discretization in the continuum region. In this work, we propose a theory based approximation for the residual based a posteriori error estimator which greatly improves the efficiency of the adaptivity. In particular, the numerically expensive modeling residual is only computed exactly in a small region around the coupling interface but replaced by a theoretically justified approximation by the coarsening residual outside that region. We present a range of adaptive computations based on our modified a posteriori error estimator and its variants for different types of crystalline defects some of which are not considered in previous related literature of the adaptive a/c methods. The numerical results show that, compared with the original residual based error estimator, the adaptive algorithm using the modified error estimator with properly chosen parameters leads to the same optimal convergence rate of the error but reduces the computational cost by one order with respect to the number of degrees of freedom.

math.NA↗

arXiv2022

The Monocular Depth Estimation Challenge

This paper summarizes the results of the first Monocular Depth Estimation Challenge (MDEC) organized at WACV2023. This challenge evaluated the progress of self-supervised monocular depth estimation on the challenging SYNS-Patches dataset. The challenge was organized on CodaLab and received submissions from 4 valid teams. Participants were provided a devkit containing updated reference implementations for 16 State-of-the-Art algorithms and 4 novel techniques. The threshold for acceptance for novel techniques was to outperform every one of the 16 SotA baselines. All participants outperformed the baseline in traditional metrics such as MAE or AbsRel. However, pointcloud reconstruction metrics were challenging to improve upon. We found predictions were characterized by interpolation artefacts at object boundaries and errors in relative object positioning. We hope this challenge is a valuable contribution to the community and encourage authors to participate in future editions.

cs.CV↗

arXiv2022

Nano-Resolution Visual Identifiers Enable Secure Monitoring in Next-Generation Cyber-Physical Systems

Today's supply chains heavily rely on cyber-physical systems such as intelligent transportation, online shopping, and E-commerce. It is advantageous to track goods in real-time by web-based registration and authentication of products after any substantial change or relocation. Despite recent advantages in technology-based tracking systems, most supply chains still rely on plainly printed tags such as barcodes and Quick Response (QR) codes for tracking purposes. Although affordable and efficient, these tags convey no security against counterfeit and cloning attacks, raising privacy concerns. It is a critical matter since a few security breaches in merchandise databases in recent years has caused crucial social and economic impacts such as identity loss, social panic, and loss of trust in the community. This paper considers an end-to-end system using dendrites as nano-resolution visual identifiers to secure supply chains. Dendrites are formed by generating fractal metallic patterns on transparent substrates through an electrochemical process, which can be used as secure identifiers due to their natural randomness, high entropy, and unclonable features. The proposed framework compromises the back-end program for identification and authentication, a web-based application for mobile devices, and a cloud database. We review architectural design, dendrite operational phases (personalization, registration, inspection), a lightweight identification method based on 2D graph-matching, and a deep 3D image authentication method based on Digital Holography (DH). A two-step search is proposed to make the system scalable by limiting the search space to samples with high similarity scores in a lower-dimensional space. We conclude by presenting our solution to make dendrites secure against adversarial attacks.

cs.CR↗

arXiv2022

Fast Key Points Detection and Matching for Tree-Structured Images

This paper offers a new authentication algorithm based on image matching of nano-resolution visual identifiers with tree-shaped patterns. The algorithm includes image-to-tree conversion by greedy extraction of the fractal pattern skeleton along with a custom-built graph matching algorithm that is robust against imaging artifacts such as scaling, rotation, scratch, and illumination change. The proposed algorithm is applicable to a variety of tree-structured image matching, but our focus is on dendrites, recently-developed visual identifiers. Dendrites are entropy rich and unclonable with existing 2D and 3D printers due to their natural randomness, nano-resolution granularity, and 3D facets, making them an appropriate choice for security applications such as supply chain trace and tracking. The proposed algorithm improves upon graph matching with standard image descriptors. For instance, image inconsistency due to the camera sensor noise may cause unexpected feature extraction leading to inaccurate tree conversion and authentication failure. Also, previous tree extraction algorithms are prohibitively slow hindering their scalability to large systems. In this paper, we fix the current issues of [1] and accelerate the key points extraction up to 10-times faster by implementing a new skeleton extraction method, a new key points searching algorithm, as well as an optimized key point matching algorithm. Using minimum enclosing circle and center points, make the algorithm robust to the choice of pattern shape. In contrast to [1] our algorithm handles general graphs with loop connections, therefore is applicable to a wider range of applications such as transportation map analysis, fingerprints, and retina vessel imaging.

cs.CV↗

arXiv2022

Topology and Polarization of Optical Vortex Fields from Atomic Phased Arrays

We developed theoretical formalism for generation of optical vortices by phased arrays of atoms. Using Jacobi-Anger expansion, we demonstrate the resulting field topology and determine the least number of array elements necessary for generation of vortices with a given topological charge. Vector vortices were considered, taking into account both spin and orbital angular momenta of electromagnetic fields. It was found that for the vortex field near the phase singularity, the transverse-position dependence of 3D polarization parameters is independent of the distance to the radiation source.

quant-ph↗

arXiv2022

Phase transitions and topological properties of the 5/2 quantum Hall states with strong Landau-level mixing

We numerically study a 5/2 fractional quantum Hall system with even number of electrons using the exact diagonalization where both the strong Landau level (LL) mixing and a finite width of the quantum well have been considered and adapted into a screened Coulomb interaction. With the principal component analysis, we are able to recognize a compressible-incompressible phase transition in the parameter space made of the magnetic field and the quantum well width by the competition between the first two leading components of the ground states wave functions, which is consistent with the low-lying spectral feature and previous works in the odd-electron system. In addition, the presence of the subdominant third component suggests an incompressible transition occurring as the LL-mixing strength grows into a certain parameter region associated with the ZnO experiments. We further investigate the strongly LL-mixed phase in this emerging region with the Hall viscosity, wave function overlaps, and the entanglement spectra. Results show it can be well described as a particle-hole symmetrized Pfaffian state with the dual topological properties of the Pfaffian and the anti-Pfaffian states.

cond-mat.mes-hall↗

arXiv2022

R$^2$F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference

Document-level natural language inference (DOCNLI) is a new challenging task in natural language processing, aiming at judging the entailment relationship between a pair of hypothesis and premise documents. Current datasets and baselines largely follow sentence-level settings, but fail to address the issues raised by longer documents. In this paper, we establish a general solution, named Retrieval, Reading and Fusion (R2F) framework, and a new setting, by analyzing the main challenges of DOCNLI: interpretability, long-range dependency, and cross-sentence inference. The basic idea of the framework is to simplify document-level task into a set of sentence-level tasks, and improve both performance and interpretability with the power of evidence. For each hypothesis sentence, the framework retrieves evidence sentences from the premise, and reads to estimate its credibility. Then the sentence-level results are fused to judge the relationship between the documents. For the setting, we contribute complementary evidence and entailment label annotation on hypothesis sentences, for interpretability study. Our experimental results show that R2F framework can obtain state-of-the-art performance and is robust for diverse evidence retrieval methods. Moreover, it can give more interpretable prediction results. Our model and code are released at https://github.com/phoenixsecularbird/R2F.

cs.CL↗