Search Results for author: Ziniu Hu

Found 17 papers, 8 papers with code

Improving Multi-Task Generalization via Regularizing Spurious Correlation

no code implementations19 May 2022 Ziniu Hu, Zhe Zhao, Xinyang Yi, Tiansheng Yao, Lichan Hong, Yizhou Sun, Ed H. Chi

First, the risk of having non-causal knowledge is higher, as the shared MTL model needs to encode all knowledge from different tasks, and causal knowledge for one task could be potentially spurious to the other.

Multi-Task Learning Representation Learning

Zero-shot Transfer Learning on Heterogeneous Graphs via Knowledge Transfer Networks

no code implementations3 Mar 2022 Minji Yoon, John Palowitch, Dustin Zelle, Ziniu Hu, Ruslan Salakhutdinov, Bryan Perozzi

We propose a zero-shot transfer learning module for HGNNs called a Knowledge Transfer Network (KTN) that transfers knowledge from label-abundant node types to zero-labeled node types through rich relational information given in the HG.

Domain Adaptation Graph Learning +1

Fuzzy Logic Based Logical Query Answering on Knowledge Graphs

no code implementations5 Aug 2021 Xuelu Chen, Ziniu Hu, Yizhou Sun

Answering complex First-Order Logical (FOL) queries on large-scale incomplete knowledge graphs (KGs) is an important yet challenging task.

Knowledge Graphs Link Prediction

Motif-Driven Contrastive Learning of Graph Representations

no code implementations23 Dec 2020 Shichang Zhang, Ziniu Hu, Arjun Subramonian, Yizhou Sun

Our framework MotIf-driven Contrastive leaRning Of Graph representations (MICRO-Graph) can: 1) use GNNs to extract motifs from large graph datasets; 2) leverage learned motifs to sample informative subgraphs for contrastive learning of GNN.

Contrastive Learning Self-Supervised Learning

GPT-GNN: Generative Pre-Training of Graph Neural Networks

2 code implementations27 Jun 2020 Ziniu Hu, Yuxiao Dong, Kuansan Wang, Kai-Wei Chang, Yizhou Sun

Graph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-structured data.

Graph Generation

Improving Neural Language Generation with Spectrum Control

no code implementations ICLR 2020 Lingxiao Wang, Jing Huang, Kevin Huang, Ziniu Hu, Guangtao Wang, Quanquan Gu

Recent Transformer-based models such as Transformer-XL and BERT have achieved huge success on various natural language processing tasks.

Language Modelling Machine Translation +3

Heterogeneous Graph Transformer

4 code implementations3 Mar 2020 Ziniu Hu, Yuxiao Dong, Kuansan Wang, Yizhou Sun

Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data.

Graph Sampling

Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks

1 code implementation NeurIPS 2019 Difan Zou, Ziniu Hu, Yewen Wang, Song Jiang, Yizhou Sun, Quanquan Gu

Original full-batch GCN training requires calculating the representation of all the nodes in the graph per GCN layer, which brings in high computation and memory costs.

Node Classification

Learning to Transfer via Modelling Multi-level Task Dependency

no code implementations25 Sep 2019 Haonan Wang, Zhenbang Wu, Ziniu Hu, Yizhou Sun

Besides, the understanding of relationships among tasks has been ignored by most of the current methods.

Multi-Task Learning

Demystifying Graph Neural Network Via Graph Filter Assessment

no code implementations25 Sep 2019 Yewen Wang, Ziniu Hu, Yusong Ye, Yizhou Sun

However, there still lacks in-depth analysis on (1) Whether there exists a best filter that can perform best on all graph data; (2) Which graph properties will influence the optimal choice of graph filter; (3) How to design appropriate filter adaptive to the graph data.

Few-Shot Representation Learning for Out-Of-Vocabulary Words

1 code implementation ACL 2019 Ziniu Hu, Ting Chen, Kai-Wei Chang, Yizhou Sun

Existing approaches for learning word embeddings often assume there are sufficient occurrences for each word in the corpus, such that the representation of words can be accurately estimated from their contexts.

Learning Word Embeddings Meta-Learning

Pre-Training Graph Neural Networks for Generic Structural Feature Extraction

no code implementations31 May 2019 Ziniu Hu, Changjun Fan, Ting Chen, Kai-Wei Chang, Yizhou Sun

With the proposed pre-training procedure, the generic structural information is learned and preserved, thus the pre-trained GNN requires less amount of labeled data and fewer domain-specific features to achieve high performance on different downstream tasks.

Denoising

Unbiased LambdaMART: An Unbiased Pairwise Learning-to-Rank Algorithm

1 code implementation16 Sep 2018 Ziniu Hu, Yang Wang, Qu Peng, Hang Li

Although click data is widely used in search systems in practice, so far the inherent bias, most notably position bias, has prevented it from being used in training of a ranker for search, i. e., learning-to-rank.

Learning-To-Rank

Emoji-Powered Representation Learning for Cross-Lingual Sentiment Classification

1 code implementation7 Jun 2018 Zhenpeng Chen, Sheng Shen, Ziniu Hu, Xuan Lu, Qiaozhu Mei, Xuanzhe Liu

To tackle this problem, cross-lingual sentiment classification approaches aim to transfer knowledge learned from one language that has abundant labeled examples (i. e., the source language, usually English) to another language with fewer labels (i. e., the target language).

Classification Cross-Lingual Sentiment Classification +4

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