arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 901 records · Page 50Linked to original sources

arXiv2024

Partial Scene Text Retrieval

The task of partial scene text retrieval involves localizing and searching for text instances that are the same or similar to a given query text from an image gallery. However, existing methods can only handle text-line instances, leaving the problem of searching for partial patches within these text-line instances unsolved due to a lack of patch annotations in the training data. To address this issue, we propose a network that can simultaneously retrieve both text-line instances and their partial patches. Our method embeds the two types of data (query text and scene text instances) into a shared feature space and measures their cross-modal similarities. To handle partial patches, our proposed approach adopts a Multiple Instance Learning (MIL) approach to learn their similarities with query text, without requiring extra annotations. However, constructing bags, which is a standard step of conventional MIL approaches, can introduce numerous noisy samples for training, and lower inference speed. To address this issue, we propose a Ranking MIL (RankMIL) approach to adaptively filter those noisy samples. Additionally, we present a Dynamic Partial Match Algorithm (DPMA) that can directly search for the target partial patch from a text-line instance during the inference stage, without requiring bags. This greatly improves the search efficiency and the performance of retrieving partial patches. The source code and dataset are available at https://github.com/lanfeng4659/PSTR.

cs.CV↗

arXiv2024

A Hybrid Loss Framework for Decomposition-based Time Series Forecasting Methods: Balancing Global and Component Errors

Accurate time series forecasting, predicting future values based on past data, is crucial for diverse industries. Many current time series methods decompose time series into multiple sub-series, applying different model architectures and training with an end-to-end overall loss for forecasting. However, this raises a question: does this overall loss prioritize the importance of critical sub-series within the decomposition for the better performance? To investigate this, we conduct a study on the impact of overall loss on existing time series methods with sequence decomposition. Our findings reveal that overall loss may introduce bias in model learning, hindering the learning of the prioritization of more significant sub-series and limiting the forecasting performance. To address this, we propose a hybrid loss framework combining the global and component losses. This framework introduces component losses for each sub-series alongside the original overall loss. It employs a dual min-max algorithm to dynamically adjust weights between the overall loss and component losses, and within component losses. This enables the model to achieve better performance of current time series methods by focusing on more critical sub-series while still maintaining a low overall loss. We integrate our loss framework into several time series methods and evaluate the performance on multiple datasets. Results show an average improvement of 0.5-2% over existing methods without any modifications to the model architectures.

cs.LG↗

arXiv2024

NeuroNURBS: Learning Efficient Surface Representations for 3D Solids

Boundary Representation (B-Rep) is the de facto representation of 3D solids in Computer-Aided Design (CAD). B-Rep solids are defined with a set of NURBS (Non-Uniform Rational B-Splines) surfaces forming a closed volume. To represent a surface, current works often employ the UV-grid approximation, i.e., sample points uniformly on the surface. However, the UV-grid method is not efficient in surface representation and sometimes lacks precision and regularity. In this work, we propose NeuroNURBS, a representation learning method to directly encode the parameters of NURBS surfaces. Our evaluation in solid generation and segmentation tasks indicates that the NeuroNURBS performs comparably and, in some cases, superior to UV-grids, but with a significantly improved efficiency: for training the surface autoencoder, GPU consumption is reduced by 86.7%; memory requirement drops by 79.9% for storing 3D solids. Moreover, adapting BrepGen for solid generation with our NeuroNURBS improves the FID from 30.04 to 27.24, and resolves the undulating issue in generated surfaces.

cs.CV↗

arXiv2024

Collaborative Participatory Research with LLM Agents in South Asia: An Empirically-Grounded Methodological Initiative and Agenda from Field Evidence in Sri Lanka

The integration of artificial intelligence into development research methodologies presents unprecedented opportunities for addressing persistent challenges in participatory research, particularly in linguistically diverse regions like South Asia. Drawing from an empirical implementation in Sri Lanka's Sinhala-speaking communities, this paper presents an empirically grounded methodological framework designed to transform participatory development research, situated in the challenging multilingual context of Sri Lanka's flood-prone Nilwala River Basin. Moving beyond conventional translation and data collection tools, this framework deploys a multi-agent system architecture that redefines how data collection, analysis, and community engagement are conducted in linguistically and culturally diverse research settings. This structured agent-based approach enables participatory research that is both scalable and responsive, ensuring that community perspectives remain integral to research outcomes. Field experiences reveal the immense potential of LLM-based systems in addressing long-standing issues in development research across resource-limited regions, offering both quantitative efficiencies and qualitative improvements in inclusivity. At a broader methodological level, this research agenda advocates for AI-driven participatory research tools that maintain ethical considerations, cultural respect, and operational efficiency, highlighting strategic pathways for deploying AI systems that reinforce community agency and equitable knowledge generation, potentially informing broader research agendas across the Global South.

cs.CY↗

arXiv2024

Variational Quantum Multi-Objective Optimization

Solving combinatorial optimization problems on near-term quantum devices has gained a lot of attraction in recent years. Currently, most works have focused on single-objective problems, whereas many real-world applications need to consider multiple, mostly conflicting objectives, such as cost and quality. We present a variational quantum optimization algorithm to solve discrete multi-objective optimization problems on quantum computers. The proposed quantum multi-objective optimization (QMOO) algorithm incorporates all cost Hamiltonians representing the classical objective functions in the quantum circuit and produces a quantum state consisting of Pareto-optimal solutions in superposition. From this state we retrieve a set of solutions and utilize the widely applied hypervolume indicator to determine its quality as an approximation to the Pareto-front. The variational parameters of the QMOO circuit are tuned by maximizing the hypervolume indicator in a quantum-classical hybrid fashion. We show the effectiveness of the proposed algorithm on several benchmark problems with up to five objectives. We investigate the influence of the classical optimizer, the circuit depth and compare to results from classical optimization algorithms. We find that the algorithm is robust to shot noise and produces good results with as low as 128 measurement shots in each iteration. These promising result open the perspective to run the algorithm on near-term quantum hardware.

quant-ph↗

arXiv2024

Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothing

Existing regression models tend to fall short in both accuracy and uncertainty estimation when the label distribution is imbalanced. In this paper, we propose a probabilistic deep learning model, dubbed variational imbalanced regression (VIR), which not only performs well in imbalanced regression but naturally produces reasonable uncertainty estimation as a byproduct. Different from typical variational autoencoders assuming I.I.D. representations (a data point's representation is not directly affected by other data points), our VIR borrows data with similar regression labels to compute the latent representation's variational distribution; furthermore, different from deterministic regression models producing point estimates, VIR predicts the entire normal-inverse-gamma distributions and modulates the associated conjugate distributions to impose probabilistic reweighting on the imbalanced data, thereby providing better uncertainty estimation. Experiments in several real-world datasets show that our VIR can outperform state-of-the-art imbalanced regression models in terms of both accuracy and uncertainty estimation. Code will soon be available at https://github.com/Wang-ML-Lab/variational-imbalanced-regression.

cs.LG↗

arXiv2024

Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling

Learners sharing similar implicit cognitive states often display comparable observable problem-solving performances. Leveraging collaborative connections among such similar learners proves valuable in comprehending human learning. Motivated by the success of collaborative modeling in various domains, such as recommender systems, we aim to investigate how collaborative signals among learners contribute to the diagnosis of human cognitive states (i.e., knowledge proficiency) in the context of intelligent education. The primary challenges lie in identifying implicit collaborative connections and disentangling the entangled cognitive factors of learners for improved explainability and controllability in learner Cognitive Diagnosis (CD). However, there has been no work on CD capable of simultaneously modeling collaborative and disentangled cognitive states. To address this gap, we present Coral, a Collaborative cognitive diagnosis model with disentangled representation learning. Specifically, Coral first introduces a disentangled state encoder to achieve the initial disentanglement of learners' states. Subsequently, a meticulously designed collaborative representation learning procedure captures collaborative signals. It dynamically constructs a collaborative graph of learners by iteratively searching for optimal neighbors in a context-aware manner. Using the constructed graph, collaborative information is extracted through node representation learning. Finally, a decoding process aligns the initial cognitive states and collaborative states, achieving co-disentanglement with practice performance reconstructions. Extensive experiments demonstrate the superior performance of Coral, showcasing significant improvements over state-of-the-art methods across several real-world datasets. Our code is available at https://github.com/bigdata-ustc/Coral.

cs.LG↗

arXiv2024

Prediction of Mode Structure Using A Novel Physics-Embedded Neural ODE Method

We designed a new artificial neural network by modifying the neural ordinary differential equation (NODE) framework to successfully predict the time evolution of the 2D mode profile in both the linear growth and nonlinear saturated stages. Starting from the magnetohydrodynamic (MHD) equations, simplifying assumptions were applied based on physical properties and symmetry considerations of the energetic-particle-driven geodesic acoustic mode (EGAM) to reduce complexity. Our approach embeds physical laws directly into the neural network architecture by exposing latent differential states, enabling the model to capture complex features in the nonlinear saturated stage that are difficult to describe analytically, and thus, the new artificial neural network is named as ExpNODE (Exposed latent state Neural ODE). ExpNODE was evaluated using a data set generated from first-principles simulations of the EGAM instability, focusing on the pre-saturated stage and the nonlinear saturated stage where the mode properties are most complex. Compared to state-of-the-art models such as ConvLSTM, ExpNODE with physical information not only achieved lower test loss but also converged faster during training. Specifically, it outperformed ConvLSTM method in both the 20-step and 40-step prediction horizons, demonstrating superior accuracy and efficiency. Additionally, the model exhibited strong generalization capabilities, accurately predicting mode profiles outside the training data set. Visual comparisons between model predictions and ground truth data showed that ExpNODE with physical information closely captured detailed features and asymmetries inherent in the EGAM dynamics that were not adequately captured by other models. These results suggest that integrating physical knowledge into neural ODE frameworks enhances their performance, and provides a powerful tool for modeling complex plasma phenomena.

physics.plasm-ph↗

arXiv2024

Chronos: Learning the Language of Time Series

We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models. Chronos tokenizes time series values using scaling and quantization into a fixed vocabulary and trains existing transformer-based language model architectures on these tokenized time series via the cross-entropy loss. We pretrained Chronos models based on the T5 family (ranging from 20M to 710M parameters) on a large collection of publicly available datasets, complemented by a synthetic dataset that we generated via Gaussian processes to improve generalization. In a comprehensive benchmark consisting of 42 datasets, and comprising both classical local models and deep learning methods, we show that Chronos models: (a) significantly outperform other methods on datasets that were part of the training corpus; and (b) have comparable and occasionally superior zero-shot performance on new datasets, relative to methods that were trained specifically on them. Our results demonstrate that Chronos models can leverage time series data from diverse domains to improve zero-shot accuracy on unseen forecasting tasks, positioning pretrained models as a viable tool to greatly simplify forecasting pipelines.

cs.LG↗

arXiv2024

Fréchet Denoised Distance: Enhancing Plausibility Evaluation for Generated Designs with Denoising Autoencoder

A great interest has arisen in using Deep Generative Models (DGM) for generative design. When assessing the quality of the generated designs, human designers focus more on structural plausibility, e.g., no missing component, rather than visual artifacts, e.g., noises or blurriness. Meanwhile, commonly used metrics such as Fréchet Inception Distance (FID) may not evaluate accurately because they are sensitive to visual artifacts and tolerant to semantic errors. As such, FID might not be suitable to assess the performance of DGMs for a generative design task. In this work, we propose to encode the to-be-evaluated images with a Denoising Autoencoder (DAE) and measure the distribution distance in the resulting latent space. Hereby, we design a novel metric Fréchet Denoised Distance (FDD). We experimentally test our FDD, FID and other state-of-the-art metrics on multiple datasets, e.g., BIKED, Seeing3DChairs, FFHQ and ImageNet. Our FDD can effectively detect implausible structures and is more consistent with structural inspections by human experts. Our source code is publicly available at https://github.com/jiajie96/FDD_pytorch.

cs.CV↗

arXiv2024

Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model

Sequential recommendation (SR) aims to predict items that users may be interested in based on their historical behavior sequences. We revisit SR from a novel information-theoretic perspective and find that conventional sequential modeling methods fail to adequately capture the randomness and unpredictability of user behavior. Inspired by fuzzy information processing theory, this paper introduces the DDSR model, which uses fuzzy sets of interaction sequences to overcome the limitations and better capture the evolution of users' real interests. Formally based on diffusion transition processes in discrete state spaces, which is unlike common diffusion models such as DDPM that operate in continuous domains. It is better suited for discrete data, using structured transitions instead of arbitrary noise introduction to avoid information loss. Additionally, to address the inefficiency of matrix transformations due to the vast discrete space, we use semantic labels derived from quantization or RQ-VAE to replace item IDs, enhancing efficiency and improving cold start issues. Testing on three public benchmark datasets shows that DDSR outperforms existing state-of-the-art methods in various settings, demonstrating its potential and effectiveness in handling SR tasks.

cs.LG↗

arXiv2024

Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models

Vision transformers (ViTs) have emerged as a significant area of focus, particularly for their capacity to be jointly trained with large language models and to serve as robust vision foundation models. Yet, the development of trustworthy explanation methods for ViTs has lagged, particularly in the context of post-hoc interpretations of ViT predictions. Existing sub-image selection approaches, such as feature-attribution and conceptual models, fall short in this regard. This paper proposes five desiderata for explaining ViTs -- faithfulness, stability, sparsity, multi-level structure, and parsimony -- and demonstrates the inadequacy of current methods in meeting these criteria comprehensively. We introduce a variational Bayesian explanation framework, dubbed ProbAbilistic Concept Explainers (PACE), which models the distributions of patch embeddings to provide trustworthy post-hoc conceptual explanations. Our qualitative analysis reveals the distributions of patch-level concepts, elucidating the effectiveness of ViTs by modeling the joint distribution of patch embeddings and ViT's predictions. Moreover, these patch-level explanations bridge the gap between image-level and dataset-level explanations, thus completing the multi-level structure of PACE. Through extensive experiments on both synthetic and real-world datasets, we demonstrate that PACE surpasses state-of-the-art methods in terms of the defined desiderata.

cs.LG↗

arXiv2024

First Proof of Principle Experiment for Muon Production with Ultrashort High Intensity Laser

Muons, which play a crucial role in both fundamental and applied physics, have traditionally been generated through proton accelerators or from cosmic rays. With the advent of ultra-short high-intensity lasers capable of accelerating electrons to GeV levels, it has become possible to generate muons in laser laboratories. In this work, we show the first proof of principle experiment for novel muon production with an ultra-short, high-intensity laser device through GeV electron beam bombardment on a lead converter target. The muon physical signal is confirmed by measuring its lifetime which is the first clear demonstration of laser-produced muons. Geant4 simulations were employed to investigate the photo-production, electro-production, and Bethe-Heitler processes response for muon generation and their subsequent detection. The results show that the dominant contributions of muons are attributed to the photo-production/electro-production and a significant yield of muons up to 0.01 $μ$/$e^-$ out of the converter target could be achieved. This laser muon source features compact, ultra-short pulse and high flux. Moreover, its implementation in a small laser laboratory is relatively straightforward, significantly reducing the barriers to entry for research in areas such as muonic X-ray elemental analysis, muon spin spectroscopy and so on.

physics.acc-ph↗

arXiv2024

Natural Counterfactuals With Necessary Backtracking

Counterfactual reasoning is pivotal in human cognition and especially important for providing explanations and making decisions. While Judea Pearl's influential approach is theoretically elegant, its generation of a counterfactual scenario often requires too much deviation from the observed scenarios to be feasible, as we show using simple examples. To mitigate this difficulty, we propose a framework of \emph{natural counterfactuals} and a method for generating counterfactuals that are more feasible with respect to the actual data distribution. Our methodology incorporates a certain amount of backtracking when needed, allowing changes in causally preceding variables to minimize deviations from realistic scenarios. Specifically, we introduce a novel optimization framework that permits but also controls the extent of backtracking with a naturalness criterion. Empirical experiments demonstrate the effectiveness of our method. The code is available at https://github.com/GuangyuanHao/natural_counterfactuals.

cs.AI↗

arXiv2024

Variational Language Concepts for Interpreting Foundation Language Models

Foundation Language Models (FLMs) such as BERT and its variants have achieved remarkable success in natural language processing. To date, the interpretability of FLMs has primarily relied on the attention weights in their self-attention layers. However, these attention weights only provide word-level interpretations, failing to capture higher-level structures, and are therefore lacking in readability and intuitiveness. To address this challenge, we first provide a formal definition of conceptual interpretation and then propose a variational Bayesian framework, dubbed VAriational Language Concept (VALC), to go beyond word-level interpretations and provide concept-level interpretations. Our theoretical analysis shows that our VALC finds the optimal language concepts to interpret FLM predictions. Empirical results on several real-world datasets show that our method can successfully provide conceptual interpretation for FLMs.

cs.LG↗

arXiv2024

Learning Unlabeled Clients Divergence for Federated Semi-Supervised Learning via Anchor Model Aggregation

Federated semi-supervised learning (FedSemi) refers to scenarios where there may be clients with fully labeled data, clients with partially labeled, and even fully unlabeled clients while preserving data privacy. However, challenges arise from client drift due to undefined heterogeneous class distributions and erroneous pseudo-labels. Existing FedSemi methods typically fail to aggregate models from unlabeled clients due to their inherent unreliability, thus overlooking unique information from their heterogeneous data distribution, leading to sub-optimal results. In this paper, we enable unlabeled client aggregation through SemiAnAgg, a novel Semi-supervised Anchor-Based federated Aggregation. SemiAnAgg learns unlabeled client contributions via an anchor model, effectively harnessing their informative value. Our key idea is that by feeding local client data to the same global model and the same consistently initialized anchor model (i.e., random model), we can measure the importance of each unlabeled client accordingly. Extensive experiments demonstrate that SemiAnAgg achieves new state-of-the-art results on four widely used FedSemi benchmarks, leading to substantial performance improvements: a 9% increase in accuracy on CIFAR-100 and a 7.6% improvement in recall on the medical dataset ISIC-18, compared with prior state-of-the-art. Code is available at: https://github.com/xmed-lab/SemiAnAgg.

cs.LG↗

arXiv2024

Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training

Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure. As a result, such approaches often struggle with hyper-parameter tuning and convergence. We consider the slicing privacy mechanism that injects noise into random low-dimensional projections of the private data, and provide strong privacy guarantees for it. These noisy projections are used for training generative models. To enable optimizing generative models using this DP approach, we introduce the smoothed-sliced $f$-divergence and show it enjoys statistical consistency. Moreover, we present a kernel-based estimator for this divergence, circumventing the need for adversarial training. Extensive numerical experiments demonstrate that our approach can generate synthetic data of higher quality compared with baselines. Beyond performance improvement, our method, by sidestepping the need for noisy gradients, offers data scientists the flexibility to adjust generator architecture and hyper-parameters, run the optimization over any number of epochs, and even restart the optimization process -- all without incurring additional privacy costs.

cs.LG↗

arXiv2024

Optical next generation reservoir computing

Artificial neural networks with internal dynamics exhibit remarkable capability in processing information. Reservoir computing (RC) is a canonical example that features rich computing expressivity and compatibility with physical implementations for enhanced efficiency. Recently, a new RC paradigm known as next generation reservoir computing (NGRC) further improves expressivity but compromises its physical openness, posing challenges for realizations in physical systems. Here we demonstrate optical NGRC with computations performed by light scattering through disordered media. In contrast to conventional optical RC implementations, we drive our optical reservoir directly with time-delayed inputs. Much like digital NGRC that relies on polynomial features of delayed inputs, our optical reservoir also implicitly generates these polynomial features for desired functionalities. By leveraging the domain knowledge of the reservoir inputs, we show that the optical NGRC not only predicts the short-term dynamics of the low-dimensional Lorenz63 and large-scale Kuramoto-Sivashinsky chaotic time series, but also replicates their long-term ergodic properties. Optical NGRC shows superiority in shorter training length, increased interpretability and fewer hyperparameters compared to conventional optical RC based on scattering media, while achieving better forecasting performance. Our optical NGRC framework may inspire the realization of NGRC in other physical RC systems, new applications beyond time-series processing, and the development of deep and parallel architectures broadly.

physics.optics↗