Search Results for author: Wenwu Zhu

Found 98 papers, 39 papers with code

Multi-sentence Video Grounding for Long Video Generation

no code implementations18 Jul 2024 Wei Feng, Xin Wang, Hong Chen, Zeyang Zhang, Wenwu Zhu

(iii) We also attempt video morphing and personalized generation methods to improve the subject consistency of long video generation, providing ablation experimental results for the subtasks of long video generation.

Moment Retrieval Retrieval +4

PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference

no code implementations6 Jul 2024 Ye Li, Chen Tang, Yuan Meng, Jiajun Fan, Zenghao Chai, Xinzhu Ma, Zhi Wang, Wenwu Zhu

We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs.

Combinatorial Optimization Decision Making

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers

1 code implementation25 Jun 2024 Lei Chen, Yuan Meng, Chen Tang, Xinzhu Ma, Jingyan Jiang, Xin Wang, Zhi Wang, Wenwu Zhu

Specifically, when quantizing DiT-XL/2 to W8A8 on ImageNet 256x256, Q-DiT achieves a remarkable reduction in FID by 1. 26 compared to the baseline.

Image Generation Quantization

Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification

no code implementations24 Jun 2024 Beini Xie, Heng Chang, Ziwei Zhang, Zeyang Zhang, Simin Wu, Xin Wang, Yuan Meng, Wenwu Zhu

To search for optimal lightweight Graph Neural Networks (GNNs), we propose a Lightweight Graph Neural Architecture Search with Graph SparsIfication and Network Pruning (GASSIP) method.

Graph Neural Network Network Pruning +2

Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox

1 code implementation15 Jun 2024 Yijun Liu, Yuan Meng, Fang Wu, Shenhao Peng, Hang Yao, Chaoyu Guan, Chen Tang, Xinzhu Ma, Zhi Wang, Wenwu Zhu

Based on this benchmark, we conduct extensive experiments with two well-known LLMs (English and Chinese) and four quantization algorithms to investigate this topic in-depth, yielding several counter-intuitive and valuable findings, e. g., models quantized using a calibration set with the same distribution as the test data are not necessarily optimal.


Causal-Aware Graph Neural Architecture Search under Distribution Shifts

no code implementations26 May 2024 Peiwen Li, Xin Wang, Zeyang Zhang, Yijian Qin, Ziwei Zhang, Jialong Wang, Yang Li, Wenwu Zhu

We propose to handle the distribution shifts in the graph architecture search process by discovering and exploiting the causal relationship between graphs and architectures to search for the optimal architectures that can generalize under distribution shifts.

Graph Embedding Neural Architecture Search +1

DisenStudio: Customized Multi-subject Text-to-Video Generation with Disentangled Spatial Control

no code implementations21 May 2024 Hong Chen, Xin Wang, YiPeng Zhang, Yuwei Zhou, Zeyang Zhang, Siao Tang, Wenwu Zhu

To tackle the problems, in this paper, we propose DisenStudio, a novel framework that can generate text-guided videos for customized multiple subjects, given few images for each subject.

Attribute Text-to-Video Generation +1

Exploring the Potential of Large Language Models in Graph Generation

no code implementations21 Mar 2024 Yang Yao, Xin Wang, Zeyang Zhang, Yijian Qin, Ziwei Zhang, Xu Chu, Yuekui Yang, Wenwu Zhu, Hong Mei

In this paper, we propose LLM4GraphGen to explore the ability of LLMs for graph generation with systematical task designs and extensive experiments.

Drug Discovery Graph Generation +1

Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts

1 code implementation NeurIPS 2023 Zeyang Zhang, Xin Wang, Ziwei Zhang, Zhou Qin, Weigao Wen, Hui Xue, Haoyang Li, Wenwu Zhu

In this paper, we discover that there exist cases with distribution shifts unobservable in the time domain while observable in the spectral domain, and propose to study distribution shifts on dynamic graphs in the spectral domain for the first time.

Link Prediction Node Classification

Unsupervised Graph Neural Architecture Search with Disentangled Self-supervision

no code implementations NeurIPS 2023 Zeyang Zhang, Xin Wang, Ziwei Zhang, Guangyao Shen, Shiqi Shen, Wenwu Zhu

To address the challenge, we propose a novel Disentangled Self-supervised Graph Neural Architecture Search (DSGAS) model, which is able to discover the optimal architectures capturing various latent graph factors in a self-supervised fashion based on unlabeled graph data.

Disentanglement Neural Architecture Search

Imputation with Inter-Series Information from Prototypes for Irregular Sampled Time Series

1 code implementation14 Jan 2024 Zhihao Yu, Xu Chu, Liantao Ma, Yasha Wang, Wenwu Zhu

To bridge this gap, we propose PRIME, a Prototype Recurrent Imputation ModEl, which integrates both intra-series and inter-series information for imputing missing values in irregularly sampled time series.

Imputation Memorization +1

Retraining-free Model Quantization via One-Shot Weight-Coupling Learning

1 code implementation CVPR 2024 Chen Tang, Yuan Meng, Jiacheng Jiang, Shuzhao Xie, Rongwei Lu, Xinzhu Ma, Zhi Wang, Wenwu Zhu

Conversely, mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers.

Model Compression Quantization

Grounding-Prompter: Prompting LLM with Multimodal Information for Temporal Sentence Grounding in Long Videos

no code implementations28 Dec 2023 Houlun Chen, Xin Wang, Hong Chen, Zihan Song, Jia Jia, Wenwu Zhu

To tackle these challenges, in this work we propose a Grounding-Prompter method, which is capable of conducting TSG in long videos through prompting LLM with multimodal information.

Denoising In-Context Learning +3

LLM4VG: Large Language Models Evaluation for Video Grounding

no code implementations21 Dec 2023 Wei Feng, Xin Wang, Hong Chen, Zeyang Zhang, Zihan Song, Yuwei Zhou, Wenwu Zhu

Recently, researchers have attempted to investigate the capability of LLMs in handling videos and proposed several video LLM models.

Image Captioning Video Grounding +1

VTimeLLM: Empower LLM to Grasp Video Moments

1 code implementation CVPR 2024 Bin Huang, Xin Wang, Hong Chen, Zihan Song, Wenwu Zhu

Large language models (LLMs) have shown remarkable text understanding capabilities, which have been extended as Video LLMs to handle video data for comprehending visual details.

Dense Video Captioning VCGBench-Diverse +6

Out-of-Distribution Generalized Dynamic Graph Neural Network with Disentangled Intervention and Invariance Promotion

no code implementations24 Nov 2023 Zeyang Zhang, Xin Wang, Ziwei Zhang, Haoyang Li, Wenwu Zhu

In this paper, we propose Disentangled Intervention-based Dynamic graph Attention networks with Invariance Promotion (I-DIDA) to handle spatio-temporal distribution shifts in dynamic graphs by discovering and utilizing invariant patterns, i. e., structures and features whose predictive abilities are stable across distribution shifts.

Graph Attention Graph Neural Network

Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing

no code implementations10 Nov 2023 Siao Tang, Xin Wang, Hong Chen, Chaoyu Guan, Zewen Wu, Yansong Tang, Wenwu Zhu

In this paper, we propose a novel post-training quantization method PCR (Progressive Calibration and Relaxing) for text-to-image diffusion models, which consists of a progressive calibration strategy that considers the accumulated quantization error across timesteps, and an activation relaxing strategy that improves the performance with negligible cost.


Lightweight Diffusion Models with Distillation-Based Block Neural Architecture Search

no code implementations8 Nov 2023 Siao Tang, Xin Wang, Hong Chen, Chaoyu Guan, Yansong Tang, Wenwu Zhu

When retraining the searched architecture, we adopt a dynamic joint loss to maintain the consistency between supernet training and subnet retraining, which also provides informative objectives for each block and shortens the paths of gradient propagation.

Neural Architecture Search

VideoDreamer: Customized Multi-Subject Text-to-Video Generation with Disen-Mix Finetuning

no code implementations2 Nov 2023 Hong Chen, Xin Wang, Guanning Zeng, YiPeng Zhang, Yuwei Zhou, Feilin Han, Wenwu Zhu

The video generator is further customized for the given multiple subjects by the proposed Disen-Mix Finetuning and Human-in-the-Loop Re-finetuning strategy, which can tackle the attribute binding problem of multi-subject generation.

Attribute Text-to-Video Generation +1

Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs

no code implementations27 Oct 2023 Yijian Qin, Xin Wang, Ziwei Zhang, Wenwu Zhu

Text-attributed graphs (TAGs) are prevalent on the web and research over TAGs such as citation networks, e-commerce networks and social networks has attracted considerable attention in the web community.

Graph Neural Network Representation Learning

LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?

1 code implementation26 Oct 2023 Zeyang Zhang, Xin Wang, Ziwei Zhang, Haoyang Li, Yijian Qin, Wenwu Zhu

Our main observations are: 1) LLMs have preliminary spatial-temporal understanding abilities on dynamic graphs, 2) Dynamic graph tasks show increasing difficulties for LLMs as the graph size and density increase, while not sensitive to the time span and data generation mechanism, 3) the proposed DST2 prompting method can help to improve LLMs' spatial-temporal understanding abilities on dynamic graphs for most tasks.

Graph Meets LLMs: Towards Large Graph Models

1 code implementation28 Aug 2023 Ziwei Zhang, Haoyang Li, Zeyang Zhang, Yijian Qin, Xin Wang, Wenwu Zhu

In order to promote applying large models for graphs forward, we present a perspective paper to discuss the challenges and opportunities associated with developing large graph models.

Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications

1 code implementation NeurIPS 2023 Xinyu Ma, Xu Chu, Yasha Wang, Yang Lin, Junfeng Zhao, Liantao Ma, Wenwu Zhu

To solve this problem, we propose a novel graph mixup algorithm called FGWMixup, which seeks a midpoint of source graphs in the Fused Gromov-Wasserstein (FGW) metric space.

Data Augmentation

DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation

1 code implementation5 May 2023 Hong Chen, YiPeng Zhang, Simin Wu, Xin Wang, Xuguang Duan, Yuwei Zhou, Wenwu Zhu

To tackle the problems, we propose DisenBooth, an identity-preserving disentangled tuning framework for subject-driven text-to-image generation.

Denoising Disentanglement +1

DELTA: Dynamic Embedding Learning with Truncated Conscious Attention for CTR Prediction

no code implementations3 May 2023 Chen Zhu, Liang Du, Hong Chen, Shuang Zhao, Zixun Sun, Xin Wang, Wenwu Zhu

To tackle this problem, inspired by the Global Workspace Theory in conscious processing, which posits that only a specific subset of the product features are pertinent while the rest can be noisy and even detrimental to human-click behaviors, we propose a CTR model that enables Dynamic Embedding Learning with Truncated Conscious Attention for CTR prediction, termed DELTA.

Click-Through Rate Prediction

SEAM: Searching Transferable Mixed-Precision Quantization Policy through Large Margin Regularization

no code implementations14 Feb 2023 Chen Tang, Kai Ouyang, Zenghao Chai, Yunpeng Bai, Yuan Meng, Zhi Wang, Wenwu Zhu

This general and dataset-independent property makes us search for the MPQ policy over a rather small-scale proxy dataset and then the policy can be directly used to quantize the model trained on a large-scale dataset.


Curriculum Graph Machine Learning: A Survey

no code implementations6 Feb 2023 Haoyang Li, Xin Wang, Wenwu Zhu

To the best of our knowledge, this paper is the first survey for curriculum graph machine learning.

Model Optimization

Improving Generalization of Meta-Learning With Inverted Regularization at Inner-Level

no code implementations CVPR 2023 Lianzhe Wang, Shiji Zhou, Shanghang Zhang, Xu Chu, Heng Chang, Wenwu Zhu

Despite the broad interest in meta-learning, the generalization problem remains one of the significant challenges in this field.


Decouple Before Interact: Multi-Modal Prompt Learning for Continual Visual Question Answering

no code implementations ICCV 2023 Zi Qian, Xin Wang, Xuguang Duan, Pengda Qin, Yuhong Li, Wenwu Zhu

Based on our formulation, we further propose MulTi-Modal PRompt LearnIng with DecouPLing bEfore InTeraction (TRIPLET), a novel approach that builds on a pre-trained vision-language model and consists of decoupled prompts and prompt interaction strategies to capture the complex interactions between modalities.

Continual Learning Language Modelling +2

Disentangled Representation Learning

no code implementations21 Nov 2022 Xin Wang, Hong Chen, Si'ao Tang, Zihao Wu, Wenwu Zhu

Disentangled Representation Learning (DRL) aims to learn a model capable of identifying and disentangling the underlying factors hidden in the observable data in representation form.

Representation Learning

Domain Generalization through the Lens of Angular Invariance

1 code implementation28 Oct 2022 Yujie Jin, Xu Chu, Yasha Wang, Wenwu Zhu

Based on the proposed term of invariance, we propose a novel deep DG method called Angular Invariance Domain Generalization Network (AIDGN).

Domain Generalization Representation Learning

NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results

no code implementations31 Aug 2022 Dustin Carrión-Ojeda, Hong Chen, Adrian El Baz, Sergio Escalera, Chaoyu Guan, Isabelle Guyon, Ihsan Ullah, Xin Wang, Wenwu Zhu

We present the design and baseline results for a new challenge in the ChaLearn meta-learning series, accepted at NeurIPS'22, focusing on "cross-domain" meta-learning.

Few-Shot Image Classification Few-Shot Learning +1

Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classification

no code implementations13 Aug 2022 Xin Wang, Heng Chang, Beini Xie, Tian Bian, Shiji Zhou, Daixin Wang, Zhiqiang Zhang, Wenwu Zhu

Graph neural networks (GNNs) have achieved tremendous success in the task of graph classification and its diverse downstream real-world applications.

Graph Classification

NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search

1 code implementation18 Jun 2022 Yijian Qin, Ziwei Zhang, Xin Wang, Zeyang Zhang, Wenwu Zhu

To the best of our knowledge, our work is the first benchmark for graph neural architecture search.

Benchmarking Graph Neural Network +1

A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions

1 code implementation15 Jun 2022 Sheng Zhou, Hongjia Xu, Zhuonan Zheng, Jiawei Chen, Zhao Li, Jiajun Bu, Jia Wu, Xin Wang, Wenwu Zhu, Martin Ester

Motivated by the tremendous success of deep learning in clustering, one of the most fundamental machine learning tasks, and the large number of recent advances in this direction, in this paper we conduct a comprehensive survey on deep clustering by proposing a new taxonomy of different state-of-the-art approaches.

Clustering Deep Clustering +1

Arbitrary Bit-width Network: A Joint Layer-Wise Quantization and Adaptive Inference Approach

no code implementations21 Apr 2022 Chen Tang, Haoyu Zhai, Kai Ouyang, Zhi Wang, Yifei Zhu, Wenwu Zhu

We propose to feed different data samples with varying quantization schemes to achieve a data-dependent dynamic inference, at a fine-grained layer level.


Learning to Solve Travelling Salesman Problem with Hardness-adaptive Curriculum

1 code implementation7 Apr 2022 Zeyang Zhang, Ziwei Zhang, Xin Wang, Wenwu Zhu

To solve these challenges, we first propose a principled hardness measurement to quantify the hardness of TSP instances.

Combinatorial Optimization

Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance

1 code implementation16 Mar 2022 Chen Tang, Kai Ouyang, Zhi Wang, Yifei Zhu, YaoWei Wang, Wen Ji, Wenwu Zhu

For example, MPQ search on ResNet18 with our indicators takes only 0. 06 s, which improves time efficiency exponentially compared to iterative search methods.


Fully Self-Supervised Learning for Semantic Segmentation

no code implementations24 Feb 2022 YuAn Wang, Wei Zhuo, Yucong Li, Zhi Wang, Qi Ju, Wenwu Zhu

To solve this problem, we proposed a bootstrapped training scheme for semantic segmentation, which fully leveraged the global semantic knowledge for self-supervision with our proposed PGG strategy and CAE module.

Clustering Segmentation +2

Out-Of-Distribution Generalization on Graphs: A Survey

1 code implementation16 Feb 2022 Haoyang Li, Xin Wang, Ziwei Zhang, Wenwu Zhu

This paper is the first systematic and comprehensive review of OOD generalization on graphs, to the best of our knowledge.

Out-of-Distribution Generalization

Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directions

1 code implementation4 Jan 2022 Xin Wang, Ziwei Zhang, Haoyang Li, Wenwu Zhu

However, as the literature on graph learning booms with a vast number of emerging methods and techniques, it becomes increasingly difficult to manually design the optimal machine learning algorithm for different graph-related tasks.

BIG-bench Machine Learning Graph Learning +1

Self-directed Machine Learning

no code implementations4 Jan 2022 Wenwu Zhu, Xin Wang, Pengtao Xie

Inspired by the concept of self-directed human learning, we introduce the principal concept of Self-directed Machine Learning (SDML) and propose a framework for SDML.

BIG-bench Machine Learning Model Selection

Revisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need?

no code implementations23 Dec 2021 Ziwei Zhang, Xin Wang, Zeyang Zhang, Peng Cui, Wenwu Zhu

Based on the experimental results, we advocate that TinvNN should be considered a new starting point and an essential baseline for further studies of transformation-invariant geometric deep learning.

Combinatorial Optimization Graph Neural Network +1

OOD-GNN: Out-of-Distribution Generalized Graph Neural Network

no code implementations7 Dec 2021 Haoyang Li, Xin Wang, Ziwei Zhang, Wenwu Zhu

Our proposed OOD-GNN employs a novel nonlinear graph representation decorrelation method utilizing random Fourier features, which encourages the model to eliminate the statistical dependence between relevant and irrelevant graph representations through iteratively optimizing the sample graph weights and graph encoder.

Graph Neural Network Out-of-Distribution Generalization

Syntax Customized Video Captioning by Imitating Exemplar Sentences

1 code implementation2 Dec 2021 Yitian Yuan, Lin Ma, Wenwu Zhu

Enhancing the diversity of sentences to describe video contents is an important problem arising in recent video captioning research.

Decoder Diversity +3

Controllable Video Captioning with an Exemplar Sentence

1 code implementation2 Dec 2021 Yitian Yuan, Lin Ma, Jingwen Wang, Wenwu Zhu

In this paper, we investigate a novel and challenging task, namely controllable video captioning with an exemplar sentence.

Caption Generation Decoder +4

Not All Low-Pass Filters are Robust in Graph Convolutional Networks

1 code implementation NeurIPS 2021 Heng Chang, Yu Rong, Tingyang Xu, Yatao Bian, Shiji Zhou, Xin Wang, Junzhou Huang, Wenwu Zhu

Graph Convolutional Networks (GCNs) are promising deep learning approaches in learning representations for graph-structured data.

Disentangled Contrastive Learning on Graphs

no code implementations NeurIPS 2021 Haoyang Li, Xin Wang, Ziwei Zhang, Zehuan Yuan, Hang Li, Wenwu Zhu

Then we propose a novel factor-wise discrimination objective in a contrastive learning manner, which can force the factorized representations to independently reflect the expressive information from different latent factors.

Contrastive Learning Self-Supervised Learning

Curriculum Disentangled Recommendation with Noisy Multi-feedback

1 code implementation NeurIPS 2021 Hong Chen, Yudong Chen, Xin Wang, Ruobing Xie, Rui Wang, Feng Xia, Wenwu Zhu

However, learning such disentangled representations from multi-feedback data is challenging because i) multi-feedback is complex: there exist complex relations among different types of feedback (e. g., click, unclick, and dislike, etc) as well as various user intentions, and ii) multi-feedback is noisy: there exists noisy (useless) information both in features and labels, which may deteriorate the recommendation performance.

Denoising Representation Learning

Asynchronous Decentralized Online Learning

no code implementations NeurIPS 2021 Jiyan Jiang, Wenpeng Zhang, Jinjie Gu, Wenwu Zhu

To overcome this problem, we study decentralized online learning in the asynchronous setting, which allows different learners to work at their own pace.

Graph Differentiable Architecture Search with Structure Learning

no code implementations NeurIPS 2021 Yijian Qin, Xin Wang, Zeyang Zhang, Wenwu Zhu

Extensive experiments on real-world graph datasets demonstrate that our proposed GASSO model is able to achieve state-of-the-art performance compared with existing baselines.

Denoising Graph structure learning +1

Meta Learning with Minimax Regularization

no code implementations29 Sep 2021 Lianzhe Wang, Shiji Zhou, Shanghang Zhang, Wenpeng Zhang, Heng Chang, Wenwu Zhu

Even though meta-learning has attracted research wide attention in recent years, the generalization problem of meta-learning is still not well addressed.

Few-Shot Learning

Multi-Objective Online Learning

no code implementations29 Sep 2021 Jiyan Jiang, Wenpeng Zhang, Shiji Zhou, Lihong Gu, Xiaodong Zeng, Wenwu Zhu

This paper presents a systematic study of multi-objective online learning.

A Survey on Temporal Sentence Grounding in Videos

no code implementations16 Sep 2021 Xiaohan Lan, Yitian Yuan, Xin Wang, Zhi Wang, Wenwu Zhu

In this survey, we give a comprehensive overview for TSGV, which i) summarizes the taxonomy of existing methods, ii) provides a detailed description of the evaluation protocols(i. e., datasets and metrics) to be used in TSGV, and iii) in-depth discusses potential problems of current benchmarking designs and research directions for further investigations.

Benchmarking Sentence +2

Online Continual Adaptation with Active Self-Training

no code implementations11 Jun 2021 Shiji Zhou, Han Zhao, Shanghang Zhang, Lianzhe Wang, Heng Chang, Zhi Wang, Wenwu Zhu

Our theoretical results show that OSAMD can fast adapt to changing environments with active queries.

Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge

no code implementations26 May 2021 Heng Chang, Yu Rong, Tingyang Xu, Wenbing Huang, Honglei Zhang, Peng Cui, Xin Wang, Wenwu Zhu, Junzhou Huang

We investigate the theoretical connections between graph signal processing and graph embedding models and formulate the graph embedding model as a general graph signal process with a corresponding graph filter.

Adversarial Attack Graph Embedding +1

Automated Machine Learning on Graphs: A Survey

2 code implementations1 Mar 2021 Ziwei Zhang, Xin Wang, Wenwu Zhu

Machine learning on graphs has been extensively studied in both academic and industry.

BIG-bench Machine Learning Graph Learning +1

MetaDelta: A Meta-Learning System for Few-shot Image Classification

1 code implementation22 Feb 2021 Yudong Chen, Chaoyu Guan, Zhikun Wei, Xin Wang, Wenwu Zhu

Meta-learning aims at learning quickly on novel tasks with limited data by transferring generic experience learned from previous tasks.

Classification Decoder +3

A Closer Look at Temporal Sentence Grounding in Videos: Dataset and Metric

no code implementations22 Jan 2021 Yitian Yuan, Xiaohan Lan, Xin Wang, Long Chen, Zhi Wang, Wenwu Zhu

All the results demonstrate that the re-organized dataset splits and new metric can better monitor the progress in TSGV.

Benchmarking Sentence +1

A Survey on Curriculum Learning

no code implementations25 Oct 2020 Xin Wang, Yudong Chen, Wenwu Zhu

We discuss works on curriculum learning within a general CL framework, elaborating on how to design a manually predefined curriculum or an automatic curriculum.

Active Learning BIG-bench Machine Learning +3

Implicit Graph Neural Networks

1 code implementation NeurIPS 2020 Fangda Gu, Heng Chang, Wenwu Zhu, Somayeh Sojoudi, Laurent El Ghaoui

Graph Neural Networks (GNNs) are widely used deep learning models that learn meaningful representations from graph-structured data.

Graph Learning

Disentangled Self-Supervision in Sequential Recommenders

1 code implementation23 Aug 2020 Jianxin Ma, Chang Zhou, Hongxia Yang, Peng Cui, Xin Wang, Wenwu Zhu

There exist two challenges: i) reconstructing a future sequence containing many behaviors is exponentially harder than reconstructing a single next behavior, which can lead to difficulty in convergence, and ii) the sequence of all future behaviors can involve many intentions, not all of which may be predictable from the sequence of earlier behaviors.


Asymmetric Transitivity Preserving Graph Embedding

1 code implementation ‏‏‎ ‎ 2020 Mingdong Ou, Peng Cui, Jian Pei, Ziwei Zhang, Wenwu Zhu

In particular, we develop a novel graph embedding algorithm, High-Order Proximity preserved Embedding (HOPE for short), which is scalable to preserve high-order proximities of large scale graphs and capable of capturing the asymmetric transitivity.

Graph Embedding Link Prediction

Spectral Graph Attention Network with Fast Eigen-approximation

no code implementations16 Mar 2020 Heng Chang, Yu Rong, Tingyang Xu, Wenbing Huang, Somayeh Sojoudi, Junzhou Huang, Wenwu Zhu

In this paper, we first introduce the attention mechanism in the spectral domain of graphs and present Spectral Graph Attention Network (SpGAT) that learns representations for different frequency components regarding weighted filters and graph wavelets bases.

Graph Attention Node Classification +1

Deep Learning for Learning Graph Representations

no code implementations2 Jan 2020 Wenwu Zhu, Xin Wang, Peng Cui

Mining graph data has become a popular research topic in computer science and has been widely studied in both academia and industry given the increasing amount of network data in the recent years.

Network Embedding

Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos

1 code implementation NeurIPS 2019 Yitian Yuan, Lin Ma, Jingwen Wang, Wei Liu, Wenwu Zhu

Temporal sentence grounding in videos aims to detect and localize one target video segment, which semantically corresponds to a given sentence.

Sentence Temporal Sentence Grounding

Learning Disentangled Representations for Recommendation

no code implementations NeurIPS 2019 Jianxin Ma, Chang Zhou, Peng Cui, Hongxia Yang, Wenwu Zhu

Our approach achieves macro disentanglement by inferring the high-level concepts associated with user intentions (e. g., to buy a shirt or a cellphone), while capturing the preference of a user regarding the different concepts separately.

Decision Making Disentanglement +1

Fast Hardware-Aware Neural Architecture Search

1 code implementation25 Oct 2019 Li Lyna Zhang, Yuqing Yang, Yuhang Jiang, Wenwu Zhu, Yunxin Liu

Unlike previous approaches that apply search algorithms on a small, human-designed search space without considering hardware diversity, we propose HURRICANE that explores the automatic hardware-aware search over a much larger search space and a two-stage search algorithm, to efficiently generate tailored models for different types of hardware.

Diversity Hardware Aware Neural Architecture Search +1

Multi-modal Deep Analysis for Multimedia

no code implementations11 Oct 2019 Wenwu Zhu, Xin Wang, Hongzhi Li

To address the two scientific problems, we investigate them from the following aspects: 1) multi-modal correlational representation: multi-modal fusion of data across different modalities, and 2) multi-modal data and knowledge fusion: multi-modal fusion of data with domain knowledge.

Question Answering Transfer Learning +2

Octave Graph Convolutional Network

no code implementations25 Sep 2019 Heng Chang, Yu Rong, Somayeh Sojoudi, Junzhou Huang, Wenwu Zhu

Many variants of Graph Convolutional Networks (GCNs) for representation learning have been proposed recently and have achieved fruitful results in various domains.

Node Classification Representation Learning

Power up! Robust Graph Convolutional Network based on Graph Powering

no code implementations25 Sep 2019 Ming Jin, Heng Chang, Wenwu Zhu, Somayeh Sojoudi

By challenging the classical graph Laplacian, we propose a new convolution operator that is provably robust in the spectral domain and is incorporated in the GCN architecture to improve expressivity and interpretability.

Adversarial Robustness

AdaCompress: Adaptive Compression for Online Computer Vision Services

1 code implementation17 Sep 2019 Hongshan Li, Yu Guo, Zhi Wang, Shu-Tao Xia, Wenwu Zhu

Then we train the agent in a reinforcement learning way to adapt it for different deep learning cloud services that act as the {\em interactive training environment} and feeding a reward with comprehensive consideration of accuracy and data size.

Multimedia Image and Video Processing

Sentence Specified Dynamic Video Thumbnail Generation

1 code implementation12 Aug 2019 Yitian Yuan, Lin Ma, Wenwu Zhu

With the tremendous growth of videos over the Internet, video thumbnails, providing video content previews, are becoming increasingly crucial to influencing users' online searching experiences.


A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Models

1 code implementation4 Aug 2019 Heng Chang, Yu Rong, Tingyang Xu, Wenbing Huang, Honglei Zhang, Peng Cui, Wenwu Zhu, Junzhou Huang

To this end, we begin by investigating the theoretical connections between graph signal processing and graph embedding models in a principled way and formulate the graph embedding model as a general graph signal process with corresponding graph filter.

Adversarial Attack Graph Embedding +2

Power up! Robust Graph Convolutional Network via Graph Powering

1 code implementation24 May 2019 Ming Jin, Heng Chang, Wenwu Zhu, Somayeh Sojoudi

By challenging the classical graph Laplacian, we propose a new convolution operator that is provably robust in the spectral domain and is incorporated in the GCN architecture to improve expressivity and interpretability.

Adversarial Robustness

Disparity-preserved Deep Cross-platform Association for Cross-platform Video Recommendation

no code implementations1 Jan 2019 Shengze Yu, Xin Wang, Wenwu Zhu, Peng Cui, Jingdong Wang

However, there remain two unsolved challenges: i) there exist inconsistencies in cross-platform association due to platform-specific disparity, and ii) data from distinct platforms may have different semantic granularities.

Deep Learning on Graphs: A Survey

1 code implementation11 Dec 2018 Ziwei Zhang, Peng Cui, Wenwu Zhu

Recently, substantial research efforts have been devoted to applying deep learning methods to graphs, resulting in beneficial advances in graph analysis techniques.

Learning-to-Ask: Knowledge Acquisition via 20 Questions

no code implementations22 Jun 2018 Yihong Chen, Bei Chen, Xuguang Duan, Jian-Guang Lou, Yue Wang, Wenwu Zhu, Yong Cao

Almost all the knowledge empowered applications rely upon accurate knowledge, which has to be either collected manually with high cost, or extracted automatically with unignorable errors.

Billion-scale Network Embedding with Iterative Random Projection

2 code implementations7 May 2018 Ziwei Zhang, Peng Cui, Haoyang Li, Xiao Wang, Wenwu Zhu

Network embedding, which learns low-dimensional vector representation for nodes in the network, has attracted considerable research attention recently.

Distributed Computing Link Prediction +2

To Find Where You Talk: Temporal Sentence Localization in Video with Attention Based Location Regression

no code implementations19 Apr 2018 Yitian Yuan, Tao Mei, Wenwu Zhu

Then, a multi-modal co-attention mechanism is introduced to generate not only video attention which reflects the global video structure, but also sentence attention which highlights the crucial details for temporal localization.

regression Sentence +1

Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks

no code implementations3 Dec 2017 Guohao Li, Hang Su, Wenwu Zhu

To address this issue, we propose a novel framework which endows the model capabilities in answering more complex questions by leveraging massive external knowledge with dynamic memory networks.

Question Answering Visual Question Answering

Structural Deep Embedding for Hyper-Networks

1 code implementation28 Nov 2017 Ke Tu, Peng Cui, Xiao Wang, Fei Wang, Wenwu Zhu

These hyper-networks pose great challenges to existing network embedding methods when the hyperedges are indecomposable, that is to say, any subset of nodes in a hyperedge cannot form another hyperedge.

Social and Information Networks

TIMERS: Error-Bounded SVD Restart on Dynamic Networks

1 code implementation27 Nov 2017 Ziwei Zhang, Peng Cui, Jian Pei, Xiao Wang, Wenwu Zhu

By setting a maximum tolerated error as a threshold, we can trigger SVD restart automatically when the margin exceeds this threshold. We prove that the time complexity of our method is linear with respect to the number of local dynamic changes, and our method is general across different types of dynamic networks.

Social and Information Networks

A Survey on Network Embedding

no code implementations23 Nov 2017 Peng Cui, Xiao Wang, Jian Pei, Wenwu Zhu

Network embedding assigns nodes in a network to low-dimensional representations and effectively preserves the network structure.

Social and Information Networks

Learning to Learn Image Classifiers with Visual Analogy

no code implementations CVPR 2019 Linjun Zhou, Peng Cui, Shiqiang Yang, Wenwu Zhu, Qi Tian

We then propose an out-of-sample embedding method to learn the embedding of a new class represented by a few samples through its visual analogy with base classes and derive the classification parameters for the new class.

Classification General Classification +1

Projection-free Distributed Online Learning in Networks

no code implementations ICML 2017 Wenpeng Zhang, Peilin Zhao, Wenwu Zhu, Steven C. H. Hoi, Tong Zhang

The conditional gradient algorithm has regained a surge of research interest in recent years due to its high efficiency in handling large-scale machine learning problems.

Font Size: Community Preserving Network Embedding

2 code implementations AAAI 2017 Xiao Wang, Peng Cui, Jing Wang, Jian Pei, Wenwu Zhu, Shiqiang Yang

While previous network embedding methods primarily preserve the microscopic structure, such as the first- and second-order proximities of nodes, the mesoscopic community structure, which is one of the most prominent feature of networks, is largely ignored.

Community Detection Network Embedding

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