Search Results for author: Minnan Luo

Found 41 papers, 18 papers with code

基于有向异构图的发票明细税收分类方法(Tax Classification of Invoice Details Based on Directed Heterogeneous Graph)

no code implementations CCL 2020 Peiyao Zhao, Qinghua Zheng, Bo Dong, Jianfei Ruan, Minnan Luo

税收是国家赖以生存的物质基础。为加快税收现代化, 方便纳税人便捷、规范开具增值税发票, 国税总局规定纳税人在税控系统开票前选择发票明细对应的税收分类才可正常开具发票。提高税收分类的准确度, 是构建税收风险指标和分析纳税人行为特征的重要基础。基于此, 本文提出了一种基于有向异构图的短文本分类模型(Heterogeneous Directed Graph Attenton Network, HDGAT), 利用发票明细间的有向信息建模, 引入外部知识, 显著地提高了发票明细的税收分类准确度。

A Unified Optimal Transport Framework for Cross-Modal Retrieval with Noisy Labels

no code implementations20 Mar 2024 Haochen Han, Minnan Luo, Huan Liu, Fang Nan

Despite the remarkable performance of previous supervised CMR methods, much of their success can be attributed to the well-annotated data.

Cross-Modal Retrieval Retrieval

Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval

1 code implementation8 Mar 2024 Haochen Han, Qinghua Zheng, Guang Dai, Minnan Luo, Jingdong Wang

To achieve this, we propose L2RM, a general framework based on Optimal Transport (OT) that learns to rematch mismatched pairs.

Cross-Modal Retrieval Retrieval +2

DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection

no code implementations16 Feb 2024 Herun Wan, Shangbin Feng, Zhaoxuan Tan, Heng Wang, Yulia Tsvetkov, Minnan Luo

Large language models are limited by challenges in factuality and hallucinations to be directly employed off-the-shelf for judging the veracity of news articles, where factual accuracy is paramount.


What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection

no code implementations1 Feb 2024 Shangbin Feng, Herun Wan, Ningnan Wang, Zhaoxuan Tan, Minnan Luo, Yulia Tsvetkov

Social media bot detection has always been an arms race between advancements in machine learning bot detectors and adversarial bot strategies to evade detection.

Towards Open-world Cross-Domain Sequential Recommendation: A Model-Agnostic Contrastive Denoising Approach

no code implementations8 Nov 2023 Wujiang Xu, Xuying Ning, Wenfang Lin, Mingming Ha, Qiongxu Ma, Qianqiao Liang, Xuewen Tao, Linxun Chen, Bing Han, Minnan Luo

Cross-domain sequential recommendation (CDSR) aims to address the data sparsity problems that exist in traditional sequential recommendation (SR) systems.

Denoising Sequential Recommendation

Disentangled Representation Learning with Transmitted Information Bottleneck

no code implementations3 Nov 2023 Zhuohang Dang, Minnan Luo, Chengyou Jia, Guang Dai, Jihong Wang, Xiaojun Chang, Jingdong Wang, Qinghua Zheng

Encoding only the task-related information from the raw data, \ie, disentangled representation learning, can greatly contribute to the robustness and generalizability of models.

Disentanglement Variational Inference

GADY: Unsupervised Anomaly Detection on Dynamic Graphs

no code implementations25 Oct 2023 Shiqi Lou, Qingyue Zhang, Shujie Yang, Yuyang Tian, Zhaoxuan Tan, Minnan Luo

Supplementary experiments further validate the effectiveness of our model design and the necessity of each module.

Unsupervised Anomaly Detection

Adversarial Attacks on Fairness of Graph Neural Networks

1 code implementation20 Oct 2023 Binchi Zhang, Yushun Dong, Chen Chen, Yada Zhu, Minnan Luo, Jundong Li

Fairness-aware graph neural networks (GNNs) have gained a surge of attention as they can reduce the bias of predictions on any demographic group (e. g., female) in graph-based applications.


PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement

no code implementations20 Sep 2023 Chengyou Jia, Minnan Luo, Zhuohang Dang, Guang Dai, Xiaojun Chang, Jingdong Wang

Dominant Person Search methods aim to localize and recognize query persons in a unified network, which jointly optimizes two sub-tasks, \ie, pedestrian detection and Re-IDentification (ReID).

Denoising Pedestrian Detection +2

SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-form Layout-to-Image Generation

no code implementations20 Aug 2023 Chengyou Jia, Minnan Luo, Zhuohang Dang, Guang Dai, Xiaojun Chang, Mengmeng Wang, Jingdong Wang

Despite significant progress in Text-to-Image (T2I) generative models, even lengthy and complex text descriptions still struggle to convey detailed controls.

Layout-to-Image Generation

Detecting Spoilers in Movie Reviews with External Movie Knowledge and User Networks

1 code implementation22 Apr 2023 Heng Wang, Wenqian Zhang, Yuyang Bai, Zhaoxuan Tan, Shangbin Feng, Qinghua Zheng, Minnan Luo

We then propose MVSD, a novel Multi-View Spoiler Detection framework that takes into account the external knowledge about movies and user activities on movie review platforms.

Noisy Correspondence Learning with Meta Similarity Correction

1 code implementation CVPR 2023 Haochen Han, Kaiyao Miao, Qinghua Zheng, Minnan Luo

Despite the success of multimodal learning in cross-modal retrieval task, the remarkable progress relies on the correct correspondence among multimedia data.

Binary Classification Cross-Modal Retrieval +1

Disentangled Generation with Information Bottleneck for Few-Shot Learning

no code implementations29 Nov 2022 Zhuohang Dang, Jihong Wang, Minnan Luo, Chengyou Jia, Caixia Yan, Qinghua Zheng

To these challenges, we propose a novel Information Bottleneck (IB) based Disentangled Generation Framework for FSL, termed as DisGenIB, that can simultaneously guarantee the discrimination and diversity of generated samples.

Disentanglement Few-Shot Learning

PAR: Political Actor Representation Learning with Social Context and Expert Knowledge

1 code implementation15 Oct 2022 Shangbin Feng, Zhaoxuan Tan, Zilong Chen, Ningnan Wang, Peisheng Yu, Qinghua Zheng, Xiaojun Chang, Minnan Luo

Extensive experiments demonstrate that PAR is better at augmenting political text understanding and successfully advances the state-of-the-art in political perspective detection and roll call vote prediction.

Representation Learning

GraTO: Graph Neural Network Framework Tackling Over-smoothing with Neural Architecture Search

1 code implementation18 Aug 2022 Xinshun Feng, Herun Wan, Shangbin Feng, Hongrui Wang, Jun Zhou, Qinghua Zheng, Minnan Luo

Further experiments bear out the quality of node representations learned with GraTO and the effectiveness of model architecture.

Neural Architecture Search

BIC: Twitter Bot Detection with Text-Graph Interaction and Semantic Consistency

1 code implementation17 Aug 2022 Zhenyu Lei, Herun Wan, Wenqian Zhang, Shangbin Feng, Zilong Chen, Jundong Li, Qinghua Zheng, Minnan Luo

In addition, given the stealing behavior of novel Twitter bots, BIC proposes to model semantic consistency in tweets based on attention weights while using it to augment the decision process.

Misinformation Twitter Bot Detection

AHEAD: A Triple Attention Based Heterogeneous Graph Anomaly Detection Approach

1 code implementation17 Aug 2022 Shujie Yang, Binchi Zhang, Shangbin Feng, Zhaoxuan Tan, Qinghua Zheng, Jun Zhou, Minnan Luo

In light of this problem, we propose AHEAD: a heterogeneity-aware unsupervised graph anomaly detection approach based on the encoder-decoder framework.

Attribute Decoder +1

KRACL: Contrastive Learning with Graph Context Modeling for Sparse Knowledge Graph Completion

1 code implementation16 Aug 2022 Zhaoxuan Tan, Zilong Chen, Shangbin Feng, Qingyue Zhang, Qinghua Zheng, Jundong Li, Minnan Luo

Knowledge Graph Embeddings (KGE) aim to map entities and relations to low dimensional spaces and have become the \textit{de-facto} standard for knowledge graph completion.

Contrastive Learning Knowledge Graph Embeddings

Towards Explanation for Unsupervised Graph-Level Representation Learning

1 code implementation20 May 2022 Qinghua Zheng, Jihong Wang, Minnan Luo, YaoLiang Yu, Jundong Li, Lina Yao, Xiaojun Chang

Due to the superior performance of Graph Neural Networks (GNNs) in various domains, there is an increasing interest in the GNN explanation problem "\emph{which fraction of the input graph is the most crucial to decide the model's decision?}"

Decision Making Graph Classification +2

Noise-Tolerant Learning for Audio-Visual Action Recognition

no code implementations16 May 2022 Haochen Han, Qinghua Zheng, Minnan Luo, Kaiyao Miao, Feng Tian, Yan Chen

To address this challenge, we use the audio-visual action recognition task as a proxy and propose a noise-tolerant learning framework to find anti-interference model parameters against both noisy labels and noisy correspondence.

Action Recognition Noise Estimation +1

KCD: Knowledge Walks and Textual Cues Enhanced Political Perspective Detection in News Media

1 code implementation NAACL 2022 Wenqian Zhang, Shangbin Feng, Zilong Chen, Zhenyu Lei, Jundong Li, Minnan Luo

Previous approaches generally focus on leveraging textual content to identify stances, while they fail to reason with background knowledge or leverage the rich semantic and syntactic textual labels in news articles.

Knowledge Graphs Representation Learning

Toward Enhanced Robustness in Unsupervised Graph Representation Learning: A Graph Information Bottleneck Perspective

no code implementations21 Jan 2022 Jihong Wang, Minnan Luo, Jundong Li, Ziqi Liu, Jun Zhou, Qinghua Zheng

Our RGIB attempts to learn robust node representations against adversarial perturbations by preserving the original information in the benign graph while eliminating the adversarial information in the adversarial graph.

Adversarial Attack Graph Learning +2

PPSGCN: A Privacy-Preserving Subgraph Sampling Based Distributed GCN Training Method

no code implementations22 Oct 2021 Binchi Zhang, Minnan Luo, Shangbin Feng, Ziqi Liu, Jun Zhou, Qinghua Zheng

In light of these problems, we propose a Privacy-Preserving Subgraph sampling based distributed GCN training method (PPSGCN), which preserves data privacy and significantly cuts back on communication and memory overhead.

Federated Learning Graph Learning +2

Reliable Shot Identification for Complex Event Detection via Visual-Semantic Embedding

no code implementations12 Oct 2021 Minnan Luo, Xiaojun Chang, Chen Gong

In this paper, we decompose the video into several segments and intuitively model the task of complex event detection as a multiple instance learning problem by representing each video as a "bag" of segments in which each segment is referred to as an instance.

Event Detection Multiple Instance Learning

Semantics-Guided Contrastive Network for Zero-Shot Object detection

no code implementations4 Sep 2021 Caixia Yan, Xiaojun Chang, Minnan Luo, Huan Liu, Xiaoqin Zhang, Qinghua Zheng

To address these issues, we develop a novel Semantics-Guided Contrastive Network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection.

Contrastive Learning Generalized Zero-Shot Object Detection +3

Legislator Representation Learning with Social Context and Expert Knowledge

1 code implementation9 Aug 2021 Shangbin Feng, Zhaoxuan Tan, Zilong Chen, Peisheng Yu, Qinghua Zheng, Xiaojun Chang, Minnan Luo

Modeling the ideological perspectives of political actors is an essential task in computational political science with applications in many downstream tasks.

Representation Learning Stance Detection

Towards Entity Alignment in the Open World: An Unsupervised Approach

1 code implementation26 Jan 2021 Weixin Zeng, Xiang Zhao, Jiuyang Tang, Xinyi Li, Minnan Luo, Qinghua Zheng

These preliminary results are regarded as the pseudo-labeled data and forwarded to the progressive learning framework to generate structural representations, which are integrated with the side information to provide a more comprehensive view for alignment.

Entity Alignment Knowledge Graphs

Self-Weighted Robust LDA for Multiclass Classification with Edge Classes

no code implementations24 Sep 2020 Caixia Yan, Xiaojun Chang, Minnan Luo, Qinghua Zheng, Xiaoqin Zhang, Zhihui Li, Feiping Nie

In this regard, a novel self-weighted robust LDA with l21-norm based pairwise between-class distance criterion, called SWRLDA, is proposed for multi-class classification especially with edge classes.

Classification Computational Efficiency +2

Scalable Attack on Graph Data by Injecting Vicious Nodes

1 code implementation22 Apr 2020 Jihong Wang, Minnan Luo, Fnu Suya, Jundong Li, Zijiang Yang, Qinghua Zheng

Recent studies have shown that graph convolution networks (GCNs) are vulnerable to carefully designed attacks, which aim to cause misclassification of a specific node on the graph with unnoticeable perturbations.

ZSTAD: Zero-Shot Temporal Activity Detection

no code implementations CVPR 2020 Lingling Zhang, Xiaojun Chang, Jun Liu, Minnan Luo, Sen Wang, ZongYuan Ge, Alexander Hauptmann

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos.

Action Detection Activity Detection

Self-Supervised Graph Representation Learning via Global Context Prediction

no code implementations3 Mar 2020 Zhen Peng, Yixiang Dong, Minnan Luo, Xiao-Ming Wu, Qinghua Zheng

To take full advantage of fast-growing unlabeled networked data, this paper introduces a novel self-supervised strategy for graph representation learning by exploiting natural supervision provided by the data itself.

Clustering Graph Representation Learning +2

Graph Representation Learning via Graphical Mutual Information Maximization

1 code implementation4 Feb 2020 Zhen Peng, Wenbing Huang, Minnan Luo, Qinghua Zheng, Yu Rong, Tingyang Xu, Junzhou Huang

The richness in the content of various information networks such as social networks and communication networks provides the unprecedented potential for learning high-quality expressive representations without external supervision.

Graph Representation Learning Link Prediction +2

Simple to Complex Cross-modal Learning to Rank

no code implementations4 Feb 2017 Minnan Luo, Xiaojun Chang, Zhihui Li, Liqiang Nie, Alexander G. Hauptmann, Qinghua Zheng

The heterogeneity-gap between different modalities brings a significant challenge to multimedia information retrieval.

Cross-Modal Retrieval Information Retrieval +3

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