Search Results for author: Wenji Mao

Found 14 papers, 4 papers with code

Variational Graph Auto-Encoder Based Inductive Learning Method for Semi-Supervised Classification

no code implementations26 Mar 2024 Hanxuan Yang, Zhaoxin Yu, Qingchao Kong, Wei Liu, Wenji Mao

Graph representation learning is a fundamental research issue in various domains of applications, of which the inductive learning problem is particularly challenging as it requires models to generalize to unseen graph structures during inference.

Graph Representation Learning Node Classification

YAYI-UIE: A Chat-Enhanced Instruction Tuning Framework for Universal Information Extraction

1 code implementation24 Dec 2023 Xinglin Xiao, Yijie Wang, Nan Xu, Yuqi Wang, Hanxuan Yang, Minzheng Wang, Yin Luo, Lei Wang, Wenji Mao, Daniel Zeng

The difficulty of the information extraction task lies in dealing with the task-specific label schemas and heterogeneous data structures.

UIE

Isomorphic-Consistent Variational Graph Auto-Encoders for Multi-Level Graph Representation Learning

no code implementations9 Dec 2023 Hanxuan Yang, Qingchao Kong, Wenji Mao

To overcome the limitations of existing unsupervised methods, in this paper, we propose the Isomorphic-Consistent VGAE (IsoC-VGAE) for multi-level task-agnostic graph representation learning.

Graph Classification Graph Learning +4

Disentangled Text Representation Learning with Information-Theoretic Perspective for Adversarial Robustness

no code implementations26 Oct 2022 Jiahao Zhao, Wenji Mao

Specifically, inspired by the variation of information (VI) in information theory, we derive a disentangled learning objective composed of mutual information to represent both the semantic representativeness of latent embeddings and differentiation of robust and non-robust features.

Adversarial Robustness Representation Learning +2

Spiking Variational Graph Auto-Encoders for Efficient Graph Representation Learning

no code implementations24 Oct 2022 Hanxuan Yang, Ruike Zhang, Qingchao Kong, Wenji Mao

Graph representation learning is a fundamental research issue and benefits a wide range of applications on graph-structured data.

Graph Representation Learning Link Prediction

A Comprehensive Empirical Study of Vision-Language Pre-trained Model for Supervised Cross-Modal Retrieval

1 code implementation8 Jan 2022 Zhixiong Zeng, Wenji Mao

Cross-Modal Retrieval (CMR) is an important research topic across multimodal computing and information retrieval, which takes one type of data as the query to retrieve relevant data of another type.

Cross-Modal Retrieval Information Retrieval +1

A Deep Latent Space Model for Directed Graph Representation Learning

no code implementations29 Sep 2021 Hanxuan Yang, Qingchao Kong, Wenji Mao

We propose a Deep Latent Space Model (DLSM) for directed graphs to incorporate the traditional latent space random graph model into deep learning frameworks via a hierarchical variational auto-encoder architecture.

Community Detection Graph Representation Learning +1

AnANet: Modeling Association and Alignment for Cross-modal Correlation Classification

no code implementations2 Sep 2021 Nan Xu, Junyan Wang, Yuan Tian, Ruike Zhang, Wenji Mao

Thus researchers study the definition of cross-modal correlation category and construct various classification systems and predictive models.

Classification

A Deep Latent Space Model for Graph Representation Learning

1 code implementation22 Jun 2021 Hanxuan Yang, Qingchao Kong, Wenji Mao

Our proposed model consists of a graph convolutional network (GCN) encoder and a stochastic decoder, which are layer-wise connected by a hierarchical variational auto-encoder architecture.

Community Detection Decoder +2

Reasoning with Multimodal Sarcastic Tweets via Modeling Cross-Modality Contrast and Semantic Association

no code implementations ACL 2020 Nan Xu, Zhixiong Zeng, Wenji Mao

In multimodal context, sarcasm is no longer a pure linguistic phenomenon, and due to the nature of social media short text, the opposite is more often manifested via cross-modality expressions.

Relation Relation Network +1

Modeling Conversation Structure and Temporal Dynamics for Jointly Predicting Rumor Stance and Veracity

no code implementations IJCNLP 2019 Penghui Wei, Nan Xu, Wenji Mao

The bottom component of our framework classifies the stances of tweets in a conversation discussing a rumor via modeling the structural property based on a novel graph convolutional network.

Multi-Task Learning Stance Classification

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