Search Results for author: Wei Hu

Found 128 papers, 57 papers with code

融合XLM词语表示的神经机器译文自动评价方法(Neural Automatic Evaluation of Machine Translation Method Combined with XLM Word Representation)

no code implementations CCL 2021 Wei Hu, Maoxi Li, Bailian Qiu, Mingwen Wang

“机器译文自动评价对机器翻译的发展和应用起着重要的促进作用, 它一般通过计算机器译文和人工参考译文的相似度来度量机器译文的质量。该文通过跨语种预训练语言模型XLM将源语言句子、机器译文和人工参考译文映射到相同的语义空间, 结合分层注意力和内部注意力提取源语言句子与机器译文、机器译文与人工参考译文以及源语言句子与人工参考译文之间差异特征, 并将其融入到基于Bi-LSTM神经译文自动评价方法中。在WMT’19译文自动评价数据集上的实验结果表明, 融合XLM词语表示的神经机器译文自动评价方法显著提高了其与人工评价的相关性。”

Machine Translation

Learning to Focus on the Foreground for Temporal Sentence Grounding

no code implementations COLING 2022 Daizong Liu, Wei Hu

Then, we develop a self-supervised coarse-to-fine paradigm to learn to locate the most query-relevant patch in each frame and aggregate them among the video for final grounding.

Video Understanding

Joint Pre-training and Local Re-training: Transferable Representation Learning on Multi-source Knowledge Graphs

1 code implementation5 Jun 2023 Zequn Sun, Jiacheng Huang, Jinghao Lin, Xiaozhou Xu, Qijin Chen, Wei Hu

We pre-train a large teacher KG embedding model over linked multi-source KGs and distill knowledge to train a student model for a task-specific KG.

Entity Alignment Knowledge Distillation +3

The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks

1 code implementation1 Jun 2023 Can Yaras, Peng Wang, Wei Hu, Zhihui Zhu, Laura Balzano, Qing Qu

Second, it allows us to better understand deep representation learning by elucidating the linear progressive separation and concentration of representations from shallow to deep layers.

Representation Learning

Robust Sparse Mean Estimation via Incremental Learning

1 code implementation24 May 2023 Jianhao Ma, Rui Ray Chen, Yinghui He, Salar Fattahi, Wei Hu

This paper presents a simple mean estimator that overcomes both challenges under moderate conditions: it runs in near-linear time and memory (both with respect to the ambient dimension) while requiring only $\tilde O(k)$ samples to recover the true mean.

Incremental Learning

Serial Contrastive Knowledge Distillation for Continual Few-shot Relation Extraction

1 code implementation11 May 2023 Xinyi Wang, Zitao Wang, Wei Hu

Continual few-shot relation extraction (RE) aims to continuously train a model for new relations with few labeled training data, of which the major challenges are the catastrophic forgetting of old relations and the overfitting caused by data sparsity.

Contrastive Learning Knowledge Distillation +2

Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection

1 code implementation CVPR 2023 Qianjiang Hu, Daizong Liu, Wei Hu

Recently, few works attempt to tackle the domain gap in objects, but still fail to adapt to the gap of varying beam-densities between two domains, which is critical to mitigate the characteristic differences of the LiDAR collectors.

3D Object Detection Autonomous Driving +2

Deep Active Alignment of Knowledge Graph Entities and Schemata

1 code implementation10 Apr 2023 Jiacheng Huang, Zequn Sun, Qijin Chen, Xiaozhou Xu, Weijun Ren, Wei Hu

With deep learning, it learns the embeddings of entities, relations and classes, and jointly aligns them in a semi-supervised manner.

Active Learning Knowledge Graphs

Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning

no code implementations4 Feb 2023 Xiangrong Zhu, Guangyao Li, Wei Hu

To cope with the drift between local optimization and global convergence caused by data heterogeneity, we propose mutual knowledge distillation to transfer local knowledge to global, and absorb global knowledge back.

Federated Learning Knowledge Distillation +2

LS-DYNA Machine Learning-based Multiscale Method for Nonlinear Modeling of Short Fiber-Reinforced Composites

no code implementations6 Jan 2023 Haoyan Wei, C. T. Wu, Wei Hu, Tung-Huan Su, Hitoshi Oura, Masato Nishi, Tadashi Naito, Stan Chung, Leo Shen

In this work, we present a machine learning-based multiscale method by integrating injection molding-induced microstructures, material homogenization, and Deep Material Network (DMN) in the finite element simulation software LS-DYNA for structural analysis of SFRC.

Transfer Learning

Open-world Story Generation with Structured Knowledge Enhancement: A Comprehensive Survey

no code implementations9 Dec 2022 Yuxin Wang, Jieru Lin, Zhiwei Yu, Wei Hu, Börje F. Karlsson

Storytelling and narrative are fundamental to human experience, intertwined with our social and cultural engagement.

Story Generation

Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs

1 code implementation29 Nov 2022 Yuanning Cui, Yuxin Wang, Zequn Sun, Wenqiang Liu, Yiqiao Jiang, Kexin Han, Wei Hu

We consider knowledge transfer and retention of the learning on growing snapshots of a KG without having to learn embeddings from scratch.

Knowledge Graphs Transfer Learning

Learning Latent Part-Whole Hierarchies for Point Clouds

no code implementations14 Nov 2022 Xiang Gao, Wei Hu, Renjie Liao

The decoder takes the latent variable and the feature from the encoder as an input and predicts the per-point part distribution at the top level.

Point Cloud Segmentation

EventEA: Benchmarking Entity Alignment for Event-centric Knowledge Graphs

1 code implementation5 Nov 2022 Xiaobin Tian, Zequn Sun, Guangyao Li, Wei Hu

Towards a critical evaluation of embedding-based entity alignment methods, we construct a new dataset with heterogeneous relations and attributes based on event-centric KGs.

Benchmarking Entity Alignment +1

Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation

1 code implementation19 Oct 2022 Botao Yu, Peiling Lu, Rui Wang, Wei Hu, Xu Tan, Wei Ye, Shikun Zhang, Tao Qin, Tie-Yan Liu

A recent trend is to use Transformer or its variants in music generation, which is, however, suboptimal, because the full attention cannot efficiently model the typically long music sequences (e. g., over 10, 000 tokens), and the existing models have shortcomings in generating musical repetition structures.

Music Generation

Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data

no code implementations13 Oct 2022 Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro, Wei Hu

In this work, we investigate the implicit bias of gradient flow and gradient descent in two-layer fully-connected neural networks with leaky ReLU activations when the training data are nearly-orthogonal, a common property of high-dimensional data.

Vocal Bursts Intensity Prediction

Large-scale Entity Alignment via Knowledge Graph Merging, Partitioning and Embedding

1 code implementation23 Aug 2022 Kexuan Xin, Zequn Sun, Wen Hua, Wei Hu, Jianfeng Qu, Xiaofang Zhou

Therefore, in this work, we propose a scalable GNN-based entity alignment approach to reduce the structure and alignment loss from three perspectives.

Entity Alignment

I Know What You Do Not Know: Knowledge Graph Embedding via Co-distillation Learning

1 code implementation21 Aug 2022 Yang Liu, Zequn Sun, Guangyao Li, Wei Hu

To this end, we propose CoLE, a Co-distillation Learning method for KG Embedding that exploits the complementarity of graph structures and text information.

Knowledge Graph Embedding Language Modelling

Neural Capture of Animatable 3D Human from Monocular Video

no code implementations18 Aug 2022 Gusi Te, Xiu Li, Xiao Li, Jinglu Wang, Wei Hu, Yan Lu

We present a novel paradigm of building an animatable 3D human representation from a monocular video input, such that it can be rendered in any unseen poses and views.

Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization

no code implementations27 Jul 2022 Daizong Liu, Wei Hu

SLP consists of a Skimming-and-Locating (SL) module and a Bi-directional Perusing (BP) module.

Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing

no code implementations27 Jul 2022 Daizong Liu, Wei Hu, Xin Li

Instead, we propose point cloud attacks from a new perspective -- the graph spectral domain attack, aiming to perturb graph transform coefficients in the spectral domain that corresponds to varying certain geometric structure.

Reducing the Vision and Language Bias for Temporal Sentence Grounding

no code implementations27 Jul 2022 Daizong Liu, Xiaoye Qu, Wei Hu

In this paper, we study the above issue of selection biases and accordingly propose a Debiasing-TSG (D-TSG) model to filter and remove the negative biases in both vision and language modalities for enhancing the model generalization ability.

Information Retrieval Retrieval

Enhancing Document-level Relation Extraction by Entity Knowledge Injection

1 code implementation23 Jul 2022 Xinyi Wang, Zitao Wang, Weijian Sun, Wei Hu

Document-level relation extraction (RE) aims to identify the relations between entities throughout an entire document.

Document-level Relation Extraction Knowledge Graphs

Facing Changes: Continual Entity Alignment for Growing Knowledge Graphs

1 code implementation23 Jul 2022 Yuxin Wang, Yuanning Cui, Wenqiang Liu, Zequn Sun, Yiqiao Jiang, Kexin Han, Wei Hu

To avoid retraining an entire model on the whole KGs whenever new entities and triples come, we present a continual alignment method for this task.

Entity Alignment Knowledge Graphs

Dynamic Point Cloud Denoising via Gradient Fields

no code implementations19 Apr 2022 Qianjiang Hu, Wei Hu

The gradient field is the gradient of the log-probability function of the noisy point cloud, based on which we perform gradient ascent so as to converge each point to the underlying clean surface.

Autonomous Driving Denoising +1

Unsupervised Manga Character Re-identification via Face-body and Spatial-temporal Associated Clustering

no code implementations10 Apr 2022 Zhimin Zhang, Zheng Wang, Wei Hu

In the past few years, there has been a dramatic growth in e-manga (electronic Japanese-style comics).

Ensemble Semi-supervised Entity Alignment via Cycle-teaching

1 code implementation12 Mar 2022 Kexuan Xin, Zequn Sun, Wen Hua, Bing Liu, Wei Hu, Jianfeng Qu, Xiaofang Zhou

We also design a conflict resolution mechanism to resolve the alignment conflict when combining the new alignment of an aligner and that from its teacher.

Entity Alignment Knowledge Graphs

More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize

no code implementations11 Mar 2022 Alexander Wei, Wei Hu, Jacob Steinhardt

On the other hand, we find that the classical GCV estimator (Craven and Wahba, 1978) accurately predicts generalization risk even in such overparameterized settings.


Multi-Scale Self-Contrastive Learning with Hard Negative Mining for Weakly-Supervised Query-based Video Grounding

no code implementations8 Mar 2022 Shentong Mo, Daizong Liu, Wei Hu

Secondly, since some predicted frames (i. e., boundary frames) are relatively coarse and exhibit similar appearance to their adjacent frames, we propose a coarse-to-fine contrastive learning paradigm to learn more discriminative frame-wise representations for distinguishing the false positive frames.

Contrastive Learning Video Grounding +1

Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding

no code implementations6 Mar 2022 Daizong Liu, Xiang Fang, Wei Hu, Pan Zhou

Temporal sentence grounding aims to localize a target segment in an untrimmed video semantically according to a given sentence query.

object-detection Object Detection +1

Sparse Graph Learning with Spectrum Prior for Deep Graph Convolutional Networks

no code implementations28 Feb 2022 Jin Zeng, Yang Liu, Gene Cheung, Wei Hu

Specifically, based on a spectral analysis of multilayer GCN output, we derive a spectrum prior for the graph Laplacian matrix $\mathbf{L}$ to robustify the model expressiveness against over-smoothing.

Graph Learning

Automated Extraction of Energy Systems Information from Remotely Sensed Data: A Review and Analysis

no code implementations18 Feb 2022 Simiao Ren, Wei Hu, Kyle Bradbury, Dylan Harrison-Atlas, Laura Malaguzzi Valeri, Brian Murray, Jordan M. Malof

These include the opportunity to extend the methods beyond electricity to broader energy systems and wider geographic areas; and the ability to expand the use of these methods in research and decision making as satellite data become cheaper and easier to access.

Decision Making Ethics

Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks

1 code implementation15 Feb 2022 Qianjiang Hu, Daizong Liu, Wei Hu

Instead, we propose point cloud attacks from a new perspective -- Graph Spectral Domain Attack (GSDA), aiming to perturb transform coefficients in the graph spectral domain that corresponds to varying certain geometric structure.

Autonomous Driving Denoising +1

Trustworthy Knowledge Graph Completion Based on Multi-sourced Noisy Data

1 code implementation21 Jan 2022 Jiacheng Huang, Yao Zhao, Wei Hu, Zhen Ning, Qijin Chen, Xiaoxia Qiu, Chengfu Huo, Weijun Ren

In this paper, we propose a new trustworthy method that exploits facts for a KG based on multi-sourced noisy data and existing facts in the KG.

Informed Multi-context Entity Alignment

1 code implementation2 Jan 2022 Kexuan Xin, Zequn Sun, Wen Hua, Wei Hu, Xiaofang Zhou

Entity alignment is a crucial step in integrating knowledge graphs (KGs) from multiple sources.

Entity Alignment Entity Embeddings +1

Representation Alignment in Neural Networks

1 code implementation15 Dec 2021 Ehsan Imani, Wei Hu, Martha White

We then highlight why alignment between the top singular vectors and the targets can speed up learning and show in a classic synthetic transfer problem that representation alignment correlates with positive and negative transfer to similar and dissimilar tasks.

Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification

no code implementations22 Nov 2021 Daizong Liu, Wei Hu

Although many efforts have been made into attack and defense on the 2D image domain in recent years, few methods explore the vulnerability of 3D models.

3D Point Cloud Classification Classification +1

Deep Point Set Resampling via Gradient Fields

no code implementations3 Nov 2021 Haolan Chen, Bi'an Du, Shitong Luo, Wei Hu

3D point clouds acquired by scanning real-world objects or scenes have found a wide range of applications including immersive telepresence, autonomous driving, surveillance, etc.

Autonomous Driving Denoising +1

Vis-TOP: Visual Transformer Overlay Processor

no code implementations21 Oct 2021 Wei Hu, Dian Xu, Zimeng Fan, Fang Liu, Yanxiang He

Vis-TOP summarizes the characteristics of all visual Transformer models and implements a three-layer and two-level transformation structure that allows the model to be switched or changed freely without changing the hardware architecture.


Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction

1 code implementation EMNLP 2021 Kailong Hao, Botao Yu, Wei Hu

Distantly supervised relation extraction (RE) automatically aligns unstructured text with relation instances in a knowledge base (KB).

Relation Extraction

Score-Based Point Cloud Denoising (Learning Gradient Fields for Point Cloud Denoising)

2 code implementations ICCV 2021 Shitong Luo, Wei Hu

Since $p * n$ is unknown at test-time, and we only need the score (i. e., the gradient of the log-probability function) to perform gradient ascent, we propose a neural network architecture to estimate the score of $p * n$ given only noisy point clouds as input.

Denoising Surface Reconstruction

RGB Image Classification with Quantum Convolutional Ansaetze

no code implementations23 Jul 2021 Yu Jing, Xiaogang Li, Yang Yang, Chonghang Wu, Wenbing Fu, Wei Hu, Yuanyuan Li, Hua Xu

With the rapid growth of qubit numbers and coherence times in quantum hardware technology, implementing shallow neural networks on the so-called Noisy Intermediate-Scale Quantum (NISQ) devices has attracted a lot of interest.

Classification Image Classification

A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning

1 code implementation29 Jun 2021 Nikunj Saunshi, Arushi Gupta, Wei Hu

An effective approach in meta-learning is to utilize multiple "train tasks" to learn a good initialization for model parameters that can help solve unseen "test tasks" with very few samples by fine-tuning from this initialization.

Meta-Learning Representation Learning

Near-Optimal Linear Regression under Distribution Shift

no code implementations23 Jun 2021 Qi Lei, Wei Hu, Jason D. Lee

Transfer learning is essential when sufficient data comes from the source domain, with scarce labeled data from the target domain.

regression Transfer Learning

Knowing the No-match: Entity Alignment with Dangling Cases

1 code implementation ACL 2021 Zequn Sun, Muhao Chen, Wei Hu

Since KGs possess different sets of entities, there could be entities that cannot find alignment across them, leading to the problem of dangling entities.

Abstention Prediction Entity Alignment +1

Self-Supervised Graph Representation Learning via Topology Transformations

1 code implementation25 May 2021 Xiang Gao, Wei Hu, Guo-Jun Qi

We formalize the proposed model from an information-theoretic perspective, by maximizing the mutual information between topology transformations and node representations before and after the transformations.

Graph Classification Graph Representation Learning +3

Learning Fine-grained Fact-Article Correspondence in Legal Cases

1 code implementation21 Apr 2021 Jidong Ge, Yunyun huang, Xiaoyu Shen, Chuanyi Li, Wei Hu

We believe that learning fine-grained correspondence between each single fact and law articles is crucial for an accurate and trustworthy AI system.

Text Matching

Diffusion Probabilistic Models for 3D Point Cloud Generation

3 code implementations CVPR 2021 Shitong Luo, Wei Hu

We present a probabilistic model for point cloud generation, which is fundamental for various 3D vision tasks such as shape completion, upsampling, synthesis and data augmentation.

Data Augmentation Point Cloud Generation

Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations

no code implementations1 Mar 2021 Xiang Gao, Wei Hu, Guo-Jun Qi

Then, we self-train a representation to capture the intrinsic 3D object representation by decoding 3D transformation parameters from the fused feature representations of multiple views before and after the transformation.

3D Object Classification 3D Object Recognition +4

Towards Principled Representation Learning for Entity Alignment

no code implementations1 Jan 2021 Lingbing Guo, Zequn Sun, Mingyang Chen, Wei Hu, Huajun Chen

In this paper, we define a typical paradigm abstracted from the existing methods, and analyze how the representation discrepancy between two potentially-aligned entities is implicitly bounded by a predefined margin in the scoring function for embedding learning.

Entity Alignment Machine Translation +1

A Point Cloud Generative Model Based on Nonequilibrium Thermodynamics

no code implementations1 Jan 2021 Shitong Luo, Wei Hu

Point cloud generation thus amounts to learning the reverse diffusion process that transforms the noise distribution to the distribution of a desired shape.

Point Cloud Generation

TopoTER: Unsupervised Learning of Topology Transformation Equivariant Representations

no code implementations1 Jan 2021 Xiang Gao, Wei Hu, Guo-Jun Qi

We formalize the TopoTER from an information-theoretic perspective, by maximizing the mutual information between topology transformations and node representations before and after the transformations.

Graph Classification

A Unified Model for Gate Level Propagation Analysis

no code implementations7 Dec 2020 Jeremy Blackstone, Wei Hu, Alric Althoff, Armaiti Ardeshiricham, Lu Zhang, Ryan Kastner

To justify our model, we prove that Precise Hardware IFT is equivalent to gate level X-propagation and imprecise fault propagation.

Hardware Architecture

Eudoxus: Characterizing and Accelerating Localization in Autonomous Machines

no code implementations2 Dec 2020 Yiming Gan, Yu Bo, Boyuan Tian, Leimeng Xu, Wei Hu, Shaoshan Liu, Qiang Liu, Yanjun Zhang, Jie Tang, Yuhao Zhu

We develop and commercialize autonomous machines, such as logistic robots and self-driving cars, around the globe.

Self-Driving Cars Hardware Architecture

AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries

2 code implementations CVPR 2021 Qianjiang Hu, Xiao Wang, Wei Hu, Guo-Jun Qi

Contrastive learning relies on constructing a collection of negative examples that are sufficiently hard to discriminate against positive queries when their representations are self-trained.

Contrastive Learning

Decentralized Knowledge Graph Representation Learning

no code implementations16 Oct 2020 Lingbing Guo, Weiqing Wang, Zequn Sun, Chenghao Liu, Wei Hu

Knowledge graph (KG) representation learning methods have achieved competitive performance in many KG-oriented tasks, among which the best ones are usually based on graph neural networks (GNNs), a powerful family of networks that learns the representation of an entity by aggregating the features of its neighbors and itself.

Entity Alignment Graph Representation Learning

Impact of Representation Learning in Linear Bandits

no code implementations ICLR 2021 Jiaqi Yang, Wei Hu, Jason D. Lee, Simon S. Du

For the finite-action setting, we present a new algorithm which achieves $\widetilde{O}(T\sqrt{kN} + \sqrt{dkNT})$ regret, where $N$ is the number of rounds we play for each bandit.

Representation Learning

Knowledge Association with Hyperbolic Knowledge Graph Embeddings

1 code implementation EMNLP 2020 Zequn Sun, Muhao Chen, Wei Hu, Chengming Wang, Jian Dai, Wei zhang

Capturing associations for knowledge graphs (KGs) through entity alignment, entity type inference and other related tasks benefits NLP applications with comprehensive knowledge representations.

Entity Alignment Knowledge Graph Embeddings +1

P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions

1 code implementation14 Sep 2020 Wei Hu, QiHao Zhao, Yangyu Huang, Fan Zhang

Learning deep neural network (DNN) classifier with noisy labels is a challenging task because the DNN can easily over-fit on these noisy labels due to its high capability.

Rule-Guided Graph Neural Networks for Recommender Systems

1 code implementation9 Sep 2020 Xinze Lyu, Guangyao Li, Jiacheng Huang, Wei Hu

However, existing work incorporated with KGs cannot capture the explicit long-range semantics between users and items meanwhile consider various connectivity between items.

Collaborative Filtering Knowledge Graphs +1

Graph Signal Processing for Geometric Data and Beyond: Theory and Applications

no code implementations5 Aug 2020 Wei Hu, Jiahao Pang, Xian-Ming Liu, Dong Tian, Chia-Wen Lin, Anthony Vetro

Geometric data acquired from real-world scenes, e. g., 2D depth images, 3D point clouds, and 4D dynamic point clouds, have found a wide range of applications including immersive telepresence, autonomous driving, surveillance, etc.

Autonomous Driving

Differentiable Manifold Reconstruction for Point Cloud Denoising

1 code implementation27 Jul 2020 Shitong Luo, Wei Hu

Afterwards, the decoder infers the underlying manifold by transforming each sampled point along with the embedded feature of its neighborhood to a local surface centered around the point.

Denoising Surface Reconstruction

Edge-aware Graph Representation Learning and Reasoning for Face Parsing

1 code implementation ECCV 2020 Gusi Te, Yinglu Liu, Wei Hu, Hailin Shi, Tao Mei

Specifically, we encode a facial image onto a global graph representation where a collection of pixels ("regions") with similar features are projected to each vertex.

Face Parsing Graph Representation Learning

The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks

no code implementations NeurIPS 2020 Wei Hu, Lechao Xiao, Ben Adlam, Jeffrey Pennington

Modern neural networks are often regarded as complex black-box functions whose behavior is difficult to understand owing to their nonlinear dependence on the data and the nonconvexity in their loss landscapes.

Signed Graph Metric Learning via Gershgorin Disc Perfect Alignment

1 code implementation15 Jun 2020 Cheng Yang, Gene Cheung, Wei Hu

Given a convex and differentiable objective $Q(\M)$ for a real symmetric matrix $\M$ in the positive definite (PD) cone -- used to compute Mahalanobis distances -- we propose a fast general metric learning framework that is entirely projection-free.

Binary Classification Metric Learning

When is Particle Filtering Efficient for Planning in Partially Observed Linear Dynamical Systems?

no code implementations10 Jun 2020 Simon S. Du, Wei Hu, Zhiyuan Li, Ruoqi Shen, Zhao Song, Jiajun Wu

Though errors in past actions may affect the future, we are able to bound the number of particles needed so that the long-run reward of the policy based on particle filtering is close to that based on exact inference.

Decision Making

TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs

1 code implementation22 Apr 2020 Zequn Sun, Jiacheng Huang, Wei Hu, Muchao Chen, Lingbing Guo, Yuzhong Qu

We refer to such contextualized representations of a relation as edge embeddings and interpret them as translations between entity embeddings.

Entity Alignment Entity Embeddings +2

Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study

1 code implementation18 Mar 2020 Farahnaz Akrami, Mohammed Samiul Saeef, Qingheng Zhang, Wei Hu, Chengkai Li

A more fundamental defect of these models is that the link prediction scenario, given such data, is non-existent in the real-world.

Knowledge Graph Completion Link Prediction

Dynamic Point Cloud Denoising via Manifold-to-Manifold Distance

no code implementations17 Mar 2020 Wei Hu, Qianjiang Hu, Zehua Wang, Xiang Gao

In particular, we define a manifold-to-manifold distance and its discrete counterpart on graphs to measure the variation-based intrinsic distance between surface patches in the temporal domain, provided that graph operators are discrete counterparts of functionals on Riemannian manifolds.

Autonomous Driving Denoising +1

A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs

1 code implementation10 Mar 2020 Zequn Sun, Qingheng Zhang, Wei Hu, Chengming Wang, Muhao Chen, Farahnaz Akrami, Chengkai Li

Recent advancement in KG embedding impels the advent of embedding-based entity alignment, which encodes entities in a continuous embedding space and measures entity similarities based on the learned embeddings.

Benchmarking Entity Alignment +1

Few-Shot Learning via Learning the Representation, Provably

no code implementations ICLR 2021 Simon S. Du, Wei Hu, Sham M. Kakade, Jason D. Lee, Qi Lei

First, we study the setting where this common representation is low-dimensional and provide a fast rate of $O\left(\frac{\mathcal{C}\left(\Phi\right)}{n_1T} + \frac{k}{n_2}\right)$; here, $\Phi$ is the representation function class, $\mathcal{C}\left(\Phi\right)$ is its complexity measure, and $k$ is the dimension of the representation.

Few-Shot Learning Representation Learning

Open Knowledge Enrichment for Long-tail Entities

1 code implementation15 Feb 2020 Ermei Cao, Difeng Wang, Jiacheng Huang, Wei Hu

In this paper, we propose a full-fledged approach to knowledge enrichment, which predicts missing properties and infers true facts of long-tail entities from the open Web.

Graph Metric Learning via Gershgorin Disc Alignment

no code implementations28 Jan 2020 Cheng Yang, Gene Cheung, Wei Hu

We propose a fast general projection-free metric learning framework, where the minimization objective $\min_{\textbf{M} \in \mathcal{S}} Q(\textbf{M})$ is a convex differentiable function of the metric matrix $\textbf{M}$, and $\textbf{M}$ resides in the set $\mathcal{S}$ of generalized graph Laplacian matrices for connected graphs with positive edge weights and node degrees.

Metric Learning

Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks

no code implementations ICLR 2020 Wei Hu, Lechao Xiao, Jeffrey Pennington

The selection of initial parameter values for gradient-based optimization of deep neural networks is one of the most impactful hyperparameter choices in deep learning systems, affecting both convergence times and model performance.

3D Hand Pose Estimation via Regularized Graph Representation Learning

no code implementations4 Dec 2019 Yiming He, Wei Hu

To this end, we propose a regularized graph representation learning under a conditional adversarial learning framework for 3D hand pose estimation, aiming to capture structural inter-dependencies of hand joints.

3D Hand Pose Estimation Graph Representation Learning

Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation

1 code implementation20 Nov 2019 Zequn Sun, Chengming Wang, Wei Hu, Muhao Chen, Jian Dai, Wei zhang, Yuzhong Qu

As the direct neighbors of counterpart entities are usually dissimilar due to the schema heterogeneity, AliNet introduces distant neighbors to expand the overlap between their neighborhood structures.

Entity Alignment Knowledge Graphs

GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformations

1 code implementation CVPR 2020 Xiang Gao, Wei Hu, Guo-Jun Qi

Recent advances in Graph Convolutional Neural Networks (GCNNs) have shown their efficiency for non-Euclidean data on graphs, which often require a large amount of labeled data with high cost.

Point Cloud Segmentation

Enhanced Convolutional Neural Tangent Kernels

no code implementations3 Nov 2019 Zhiyuan Li, Ruosong Wang, Dingli Yu, Simon S. Du, Wei Hu, Ruslan Salakhutdinov, Sanjeev Arora

An exact algorithm to compute CNTK (Arora et al., 2019) yielded the finding that classification accuracy of CNTK on CIFAR-10 is within 6-7% of that of that of the corresponding CNN architecture (best figure being around 78%) which is interesting performance for a fixed kernel.

Data Augmentation regression

Joint Learning of Graph Representation and Node Features in Graph Convolutional Neural Networks

1 code implementation11 Sep 2019 Jiaxiang Tang, Wei Hu, Xiang Gao, Zongming Guo

In particular, we cast the graph optimization problem as distance metric learning to capture pairwise similarities of features in each layer.

Graph Learning Metric Learning

Leveraging Frequent Query Substructures to Generate Formal Queries for Complex Question Answering

no code implementations IJCNLP 2019 Jiwei Ding, Wei Hu, Qixin Xu, Yuzhong Qu

Formal query generation aims to generate correct executable queries for question answering over knowledge bases (KBs), given entity and relation linking results.

Question Answering Relation Linking

Feature Graph Learning for 3D Point Cloud Denoising

no code implementations22 Jul 2019 Wei Hu, Xiang Gao, Gene Cheung, Zongming Guo

In this work, we assume instead the availability of a relevant feature vector $\mathbf{f}_i$ per node $i$, from which we compute an optimal feature graph via optimization of a feature metric.

Graph Learning Image Denoising

Implicit Regularization in Deep Matrix Factorization

1 code implementation NeurIPS 2019 Sanjeev Arora, Nadav Cohen, Wei Hu, Yuping Luo

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity."

Matrix Completion

Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee

no code implementations ICLR 2020 Wei Hu, Zhiyuan Li, Dingli Yu

Over-parameterized deep neural networks trained by simple first-order methods are known to be able to fit any labeling of data.

Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs

1 code implementation13 May 2019 Lingbing Guo, Zequn Sun, Wei Hu

Moreover, triple-level learning is insufficient for the propagation of semantic information among entities, especially for the case of cross-KG embedding.

Entity Alignment Knowledge Graphs

3D Dynamic Point Cloud Denoising via Spatial-Temporal Graph Learning

no code implementations28 Apr 2019 Wei Hu, Qianjiang Hu, Zehua Wang, Xiang Gao

Finally, based on the spatial-temporal graph learning, we formulate dynamic point cloud denoising as the joint optimization of the desired point cloud and underlying spatio-temporal graph, which leverages both intra-frame affinities and inter-frame consistency and is solved via alternating minimization.

Denoising graph construction +1

On Exact Computation with an Infinitely Wide Neural Net

2 code implementations NeurIPS 2019 Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang

An attraction of such ideas is that a pure kernel-based method is used to capture the power of a fully-trained deep net of infinite width.

Gaussian Processes

Exploring Structure-Adaptive Graph Learning for Robust Semi-Supervised Classification

no code implementations23 Apr 2019 Xiang Gao, Wei Hu, Zongming Guo

In this paper, we propose Graph Learning Neural Networks (GLNNs), which exploit the optimization of graphs (the adjacency matrix in particular) from both data and tasks.

General Classification Graph Learning +1

3D Dynamic Point Cloud Inpainting via Temporal Consistency on Graphs

no code implementations23 Apr 2019 Zeqing Fu, Wei Hu, Zongming Guo

With the development of 3D laser scanning techniques and depth sensors, 3D dynamic point clouds have attracted increasing attention as a representation of 3D objects in motion, enabling various applications such as 3D immersive tele-presence, gaming and navigation.

Noise-Tolerant Paradigm for Training Face Recognition CNNs

2 code implementations CVPR 2019 Wei Hu, Yangyu Huang, Fan Zhang, Ruirui Li

Benefit from large-scale training datasets, deep Convolutional Neural Networks(CNNs) have achieved impressive results in face recognition(FR).

Face Recognition

What you get is not always what you see: pitfalls in solar array assessment using overhead imagery

2 code implementations28 Feb 2019 Wei Hu, Kyle Bradbury, Jordan M. Malof, Boning Li, Bohao Huang, Artem Streltsov, K. Sydny Fujita, Ben Hoen

Our findings suggest that traditional performance evaluation of the automated identification of solar PV from satellite imagery may be optimistic due to common limitations in the validation process.

Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

no code implementations24 Jan 2019 Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruosong Wang

This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and provides the following improvements over recent works: (i) Using a tighter characterization of training speed than recent papers, an explanation for why training a neural net with random labels leads to slower training, as originally observed in [Zhang et al. ICLR'17].

Width Provably Matters in Optimization for Deep Linear Neural Networks

no code implementations24 Jan 2019 Simon S. Du, Wei Hu

We prove that for an $L$-layer fully-connected linear neural network, if the width of every hidden layer is $\tilde\Omega (L \cdot r \cdot d_{\mathrm{out}} \cdot \kappa^3 )$, where $r$ and $\kappa$ are the rank and the condition number of the input data, and $d_{\mathrm{out}}$ is the output dimension, then gradient descent with Gaussian random initialization converges to a global minimum at a linear rate.

Feature Preserving and Uniformity-controllable Point Cloud Simplification on Graph

no code implementations29 Dec 2018 Junkun Qi, Wei Hu, Zongming Guo

With the development of 3D sensing technologies, point clouds have attracted increasing attention in a variety of applications for 3D object representation, such as autonomous driving, 3D immersive tele-presence and heritage reconstruction.

Autonomous Driving Point Cloud Registration

Optimized Skeleton-based Action Recognition via Sparsified Graph Regression

no code implementations29 Nov 2018 Xiang Gao, Wei Hu, Jiaxiang Tang, Jiaying Liu, Zongming Guo

In this paper, we represent skeletons naturally on graphs, and propose a graph regression based GCN (GR-GCN) for skeleton-based action recognition, aiming to capture the spatio-temporal variation in the data.

Action Recognition graph construction +4

Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks

no code implementations28 Nov 2018 Wei Hu, Gusi Te, Ju He, Dong Chen, Zongming Guo

Face anti-spoofing plays a crucial role in protecting face recognition systems from various attacks.

Face Anti-Spoofing Face Recognition

Recurrent Skipping Networks for Entity Alignment

no code implementations6 Nov 2018 Lingbing Guo, Zequn Sun, Ermei Cao, Wei Hu

We consider the problem of learning knowledge graph (KG) embeddings for entity alignment (EA).

Entity Alignment

DSKG: A Deep Sequential Model for Knowledge Graph Completion

1 code implementation30 Oct 2018 Lingbing Guo, Qingheng Zhang, Weiyi Ge, Wei Hu, Yuzhong Qu

Knowledge graph (KG) completion aims to fill the missing facts in a KG, where a fact is represented as a triple in the form of $(subject, relation, object)$.

Knowledge Graph Completion

A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks

no code implementations ICLR 2019 Sanjeev Arora, Nadav Cohen, Noah Golowich, Wei Hu

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data.

Local Frequency Interpretation and Non-Local Self-Similarity on Graph for Point Cloud Inpainting

no code implementations28 Sep 2018 Zeqing Fu, Wei Hu, Zongming Guo

Hence, leveraging on recent advances in graph signal processing, we propose an efficient point cloud inpainting method, exploiting both the local smoothness and the non-local self-similarity in point clouds.

Matrix Linear Discriminant Analysis

no code implementations24 Sep 2018 Wei Hu, Weining Shen, Hua Zhou, Dehan Kong

We propose a novel linear discriminant analysis approach for the classification of high-dimensional matrix-valued data that commonly arises from imaging studies.

General Classification regression

RGCNN: Regularized Graph CNN for Point Cloud Segmentation

no code implementations8 Jun 2018 Gusi Te, Wei Hu, Zongming Guo, Amin Zheng

Leveraging on spectral graph theory, we treat features of points in a point cloud as signals on graph, and define the convolution over graph by Chebyshev polynomial approximation.

Point Cloud Classification Point Cloud Segmentation +1

Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced

no code implementations NeurIPS 2018 Simon S. Du, Wei Hu, Jason D. Lee

Using a discretization argument, we analyze gradient descent with positive step size for the non-convex low-rank asymmetric matrix factorization problem without any regularization.

TreeSegNet: Adaptive Tree CNNs for Subdecimeter Aerial Image Segmentation

no code implementations29 Apr 2018 Kai Yue, Lei Yang, Ruirui Li, Wei Hu, Fan Zhang, Wei Li

For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions.

Image Segmentation Semantic Segmentation

Online Improper Learning with an Approximation Oracle

no code implementations NeurIPS 2018 Elad Hazan, Wei Hu, Yuanzhi Li, Zhiyuan Li

We revisit the question of reducing online learning to approximate optimization of the offline problem.

SeqFace: Make full use of sequence information for face recognition

1 code implementation17 Mar 2018 Wei Hu, Yangyu Huang, Fan Zhang, Ruirui Li, Wei Li, Guodong Yuan

Deep convolutional neural networks (CNNs) have greatly improved the Face Recognition (FR) performance in recent years.

Face Recognition Face Verification

An Analysis of the t-SNE Algorithm for Data Visualization

no code implementations5 Mar 2018 Sanjeev Arora, Wei Hu, Pravesh K. Kothari

A first line of attack in exploratory data analysis is data visualization, i. e., generating a 2-dimensional representation of data that makes clusters of similar points visually identifiable.

Data Visualization Dimensionality Reduction

Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong Convexity

no code implementations5 Feb 2018 Simon S. Du, Wei Hu

We consider the convex-concave saddle point problem $\min_{x}\max_{y} f(x)+y^\top A x-g(y)$ where $f$ is smooth and convex and $g$ is smooth and strongly convex.

Nearly Optimal Dynamic $k$-Means Clustering for High-Dimensional Data

no code implementations1 Feb 2018 Wei Hu, Zhao Song, Lin F. Yang, Peilin Zhong

We consider the $k$-means clustering problem in the dynamic streaming setting, where points from a discrete Euclidean space $\{1, 2, \ldots, \Delta\}^d$ can be dynamically inserted to or deleted from the dataset.

Vocal Bursts Intensity Prediction

Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding

1 code implementation16 Aug 2017 Zequn Sun, Wei Hu, Chengkai Li

Our experimental results on real-world datasets show that this approach significantly outperforms the state-of-the-art embedding approaches for cross-lingual entity alignment and could be complemented with methods based on machine translation.

Entity Alignment Machine Translation +1

Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls

no code implementations NeurIPS 2017 Zeyuan Allen-Zhu, Elad Hazan, Wei Hu, Yuanzhi Li

We propose a rank-$k$ variant of the classical Frank-Wolfe algorithm to solve convex optimization over a trace-norm ball.

PDD Graph: Bridging Electronic Medical Records and Biomedical Knowledge Graphs via Entity Linking

no code implementations17 Jul 2017 Meng Wang, Jiaheng Zhang, Jun Liu, Wei Hu, Sen Wang, Xue Li, Wenqiang Liu

Electronic medical records contain multi-format electronic medical data that consist of an abundance of medical knowledge.

Entity Linking Knowledge Graphs

Combinatorial Multi-Armed Bandit with General Reward Functions

no code implementations NeurIPS 2016 Wei Chen, Wei Hu, Fu Li, Jian Li, Yu Liu, Pinyan Lu

Our framework enables a much larger class of reward functions such as the $\max()$ function and nonlinear utility functions.

Real-time Decolorization using Dominant Colors

no code implementations10 Apr 2014 Wei Hu, Wei Li, Fan Zhang, Qian Du

Decolorization is the process to convert a color image or video to its grayscale version, and it has received great attention in recent years.

Cannot find the paper you are looking for? You can Submit a new open access paper.