Search Results for author: Tengfei Ma

Found 52 papers, 22 papers with code

Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport

1 code implementation EMNLP 2021 Manling Li, Tengfei Ma, Mo Yu, Lingfei Wu, Tian Gao, Heng Ji, Kathleen McKeown

Timeline Summarization identifies major events from a news collection and describes them following temporal order, with key dates tagged.

Timeline Summarization

Neuro-symbolic Models for Interpretable Time Series Classification using Temporal Logic Description

no code implementations15 Sep 2022 Ruixuan Yan, Tengfei Ma, Achille Fokoue, Maria Chang, Agung Julius

In this study, we present Neuro-Symbolic Time Series Classification (NSTSC), a neuro-symbolic model that leverages signal temporal logic (STL) and neural network (NN) to accomplish TSC tasks using multi-view data representation and expresses the model as a human-readable, interpretable formula.

Interpretable Machine Learning Time Series Classification

When Does A Spectral Graph Neural Network Fail in Node Classification?

no code implementations16 Feb 2022 Zhixian Chen, Tengfei Ma, Yang Wang

Although graph filters provide theoretical foundations for model explanations, it is unclear when a spectral GNN will fail.

Graph Learning Node Classification

Neural Approximation of Graph Topological Features

1 code implementation28 Jan 2022 Zuoyu Yan, Tengfei Ma, Liangcai Gao, Zhi Tang, Yusu Wang, Chao Chen

Topological features based on persistent homology capture high-order structural information so as to augment graph neural network methods.

Graph Learning Graph Representation Learning +1

Cycle Representation Learning for Inductive Relation Prediction

1 code implementation6 Oct 2021 Zuoyu Yan, Tengfei Ma, Liangcai Gao, Zhi Tang, Chao Chen

In this paper, we consider rules as cycles and show that the space of cycles has a unique structure based on the mathematics of algebraic topology.

Graph Representation Learning Inductive Relation Prediction

Graph Information Matters: Understanding Graph Filters from Interaction Probability

no code implementations29 Sep 2021 Zhixian Chen, Tengfei Ma, Yang Wang

We show that the homophily degree of graphs significantly affects the prediction error of graph filters.

Graph Learning Node Classification

Revisiting Virtual Nodes in Graph Neural Networks for Link Prediction

no code implementations29 Sep 2021 EunJeong Hwang, Veronika Thost, Shib Sankar Dasgupta, Tengfei Ma

It is well known that the graph classification performance of graph neural networks often improves by adding an artificial virtual node to the graphs, which is connected to all nodes in the graph.

Graph Classification Link Prediction

Federated Inference through Aligning Local Representations and Learning a Consensus Graph

no code implementations29 Sep 2021 Tengfei Ma, Trong Nghia Hoang, Jie Chen

On the top is a federation of the local data representations, performing global inference that incorporates all distributed parts collectively.

Federated Learning

Improving Inductive Link Prediction Using Hyper-Relational Facts

1 code implementation10 Jul 2021 Mehdi Ali, Max Berrendorf, Mikhail Galkin, Veronika Thost, Tengfei Ma, Volker Tresp, Jens Lehmann

In this work, we classify different inductive settings and study the benefits of employing hyper-relational KGs on a wide range of semi- and fully inductive link prediction tasks powered by recent advancements in graph neural networks.

Inductive Link Prediction Knowledge Graphs

Wasserstein Graph Neural Networks for Graphs with Missing Attributes

no code implementations6 Feb 2021 Zhixian Chen, Tengfei Ma, Yangqiu Song, Yang Wang

In this paper, we propose an innovative node representation learning framework, Wasserstein Graph Neural Network (WGNN), to mitigate the problem.

Graph Representation Learning Imputation +2

Multi-level Graph Matching Networks for Deep and Robust Graph Similarity Learning

no code implementations1 Jan 2021 Xiang Ling, Lingfei Wu, Saizhuo Wang, Tengfei Ma, Fangli Xu, Alex X. Liu, Chunming Wu, Shouling Ji

The proposed MGMN model consists of a node-graph matching network for effectively learning cross-level interactions between nodes of a graph and the other whole graph, and a siamese graph neural network to learn global-level interactions between two graphs.

Graph Classification Graph Matching +1

Ricci-GNN: Defending Against Structural Attacks Through a Geometric Approach

no code implementations1 Jan 2021 Ze Ye, Tengfei Ma, Chien-Chun Ni, Kin Sum Liu, Jie Gao, Chao Chen

We propose a novel GNN defense algorithm against structural attacks that maliciously modify graph topology.

GNNLens: A Visual Analytics Approach for Prediction Error Diagnosis of Graph Neural Networks

no code implementations22 Nov 2020 Zhihua Jin, Yong Wang, Qianwen Wang, Yao Ming, Tengfei Ma, Huamin Qu

Two case studies and interviews with domain experts demonstrate the effectiveness of GNNLens in facilitating the understanding of GNN models and their errors.

Node Classification

Exploiting Heterogeneous Graph Neural Networks with Latent Worker/Task Correlation Information for Label Aggregation in Crowdsourcing

no code implementations25 Oct 2020 Hanlu Wu, Tengfei Ma, Lingfei Wu, Shouling Ji

Besides, we exploit the unknown latent interaction between the same type of nodes (workers or tasks) by adding a homogeneous attention layer in the graph neural networks.

Deep Graph Matching and Searching for Semantic Code Retrieval

no code implementations24 Oct 2020 Xiang Ling, Lingfei Wu, Saizhuo Wang, Gaoning Pan, Tengfei Ma, Fangli Xu, Alex X. Liu, Chunming Wu, Shouling Ji

To this end, we first represent both natural language query texts and programming language code snippets with the unified graph-structured data, and then use the proposed graph matching and searching model to retrieve the best matching code snippet.

Graph Matching Retrieval

Unsupervised Reference-Free Summary Quality Evaluation via Contrastive Learning

1 code implementation EMNLP 2020 Hanlu Wu, Tengfei Ma, Lingfei Wu, Tariro Manyumwa, Shouling Ji

Experiments on Newsroom and CNN/Daily Mail demonstrate that our new evaluation method outperforms other metrics even without reference summaries.

Contrastive Learning Document Summarization +1

Multilevel Graph Matching Networks for Deep Graph Similarity Learning

1 code implementation8 Jul 2020 Xiang Ling, Lingfei Wu, Saizhuo Wang, Tengfei Ma, Fangli Xu, Alex X. Liu, Chunming Wu, Shouling Ji

In particular, the proposed MGMN consists of a node-graph matching network for effectively learning cross-level interactions between each node of one graph and the other whole graph, and a siamese graph neural network to learn global-level interactions between two input graphs.

Graph Classification Graph Matching +3

CHEER: Rich Model Helps Poor Model via Knowledge Infusion

no code implementations21 May 2020 Cao Xiao, Trong Nghia Hoang, Shenda Hong, Tengfei Ma, Jimeng Sun

There is a growing interest in applying deep learning (DL) to healthcare, driven by the availability of data with multiple feature channels in rich-data environments (e. g., intensive care units).

Repurpose Open Data to Discover Therapeutics for COVID-19 using Deep Learning

no code implementations21 May 2020 Xiangxiang Zeng, Xiang Song, Tengfei Ma, Xiaoqin Pan, Yadi Zhou, Yuan Hou, Zheng Zhang, George Karypis, Feixiong Cheng

While this study, by no means recommends specific drugs, it demonstrates a powerful deep learning methodology to prioritize existing drugs for further investigation, which holds the potential of accelerating therapeutic development for COVID-19.


Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport

1 code implementation24 Dec 2019 Tengfei Ma, Jie Chen

Both the coarsening matrix and the transport cost matrix are parameterized, so that an optimal coarsening strategy can be learned and tailored for a given set of graphs.

Graph Classification

Pre-Training BERT on Domain Resources for Short Answer Grading

no code implementations IJCNLP 2019 Chul Sung, Tejas Dhamecha, Swarnadeep Saha, Tengfei Ma, Vinay Reddy, Rishi Arora

Pre-trained BERT contextualized representations have achieved state-of-the-art results on multiple downstream NLP tasks by fine-tuning with task-specific data.

Language Modelling

Graph Enhanced Cross-Domain Text-to-SQL Generation

no code implementations WS 2019 Siyu Huo, Tengfei Ma, Jie Chen, Maria Chang, Lingfei Wu, Michael Witbrock

Semantic parsing is a fundamental problem in natural language understanding, as it involves the mapping of natural language to structured forms such as executable queries or logic-like knowledge representations.

Natural Language Understanding Semantic Parsing +3

GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks

no code implementations4 Oct 2019 Tengfei Ma, Junyuan Shang, Cao Xiao, Jimeng Sun

We propose the graph energy neural network (GENN) to explicitly model link type correlations.

Link Prediction

Hierarchical Graph Matching Networks for Deep Graph Similarity Learning

no code implementations25 Sep 2019 Xiang Ling, Lingfei Wu, Saizhuo Wang, Tengfei Ma, Fangli Xu, Chunming Wu, Shouling Ji

The proposed HGMN model consists of a multi-perspective node-graph matching network for effectively learning cross-level interactions between parts of a graph and a whole graph, and a siamese graph neural network for learning global-level interactions between two graphs.

Graph Matching Graph Similarity

DeepDrawing: A Deep Learning Approach to Graph Drawing

no code implementations17 Jul 2019 Yong Wang, Zhihua Jin, Qianwen Wang, Weiwei Cui, Tengfei Ma, Huamin Qu

Node-link diagrams are widely used to facilitate network explorations.

Pre-training of Graph Augmented Transformers for Medication Recommendation

1 code implementation2 Jun 2019 Junyuan Shang, Tengfei Ma, Cao Xiao, Jimeng Sun

G-BERT is the first to bring the language model pre-training schema into the healthcare domain and it achieved state-of-the-art performance on the medication recommendation task.

Language Modelling Representation Learning +1

CGNF: Conditional Graph Neural Fields

no code implementations ICLR 2019 Tengfei Ma, Cao Xiao, Junyuan Shang, Jimeng Sun

By integrating the conditional random fields (CRF) in the graph convolutional networks, we explicitly model a joint probability of the entire set of node labels, thus taking advantage of neighborhood label information in the node label prediction task.

General Classification Node Classification

EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

8 code implementations26 Feb 2019 Aldo Pareja, Giacomo Domeniconi, Jie Chen, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, Tim Kaler, Tao B. Schardl, Charles E. Leiserson

Existing approaches typically resort to node embeddings and use a recurrent neural network (RNN, broadly speaking) to regulate the embeddings and learn the temporal dynamics.

Dynamic Link Prediction Edge Classification +3

Reaching Data Confidentiality and Model Accountability on the CalTrain

no code implementations7 Dec 2018 Zhongshu Gu, Hani Jamjoom, Dong Su, Heqing Huang, Jialong Zhang, Tengfei Ma, Dimitrios Pendarakis, Ian Molloy

We also demonstrate that when malicious training participants tend to implant backdoors during model training, CALTRAIN can accurately and precisely discover the poisoned and mislabeled training data that lead to the runtime mispredictions.

Data Poisoning

Scalable Graph Learning for Anti-Money Laundering: A First Look

2 code implementations30 Nov 2018 Mark Weber, Jie Chen, Toyotaro Suzumura, Aldo Pareja, Tengfei Ma, Hiroki Kanezashi, Tim Kaler, Charles E. Leiserson, Tao B. Schardl

Organized crime inflicts human suffering on a genocidal scale: the Mexican drug cartels have murdered 150, 000 people since 2006, upwards of 700, 000 people per year are "exported" in a human trafficking industry enslaving an estimated 40 million people.

Graph Learning

AWE: Asymmetric Word Embedding for Textual Entailment

no code implementations11 Sep 2018 Tengfei Ma, Chiamin Wu, Cao Xiao, Jimeng Sun

It refers to the directional relation between text fragments such that the "premise" can infer "hypothesis".

Natural Language Inference Paraphrase Identification +2

Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders

1 code implementation NeurIPS 2018 Tengfei Ma, Jie Chen, Cao Xiao

We focus on the matrix representation of graphs and formulate penalty terms that regularize the output distribution of the decoder to encourage the satisfaction of validity constraints.

Time Series

RDPD: Rich Data Helps Poor Data via Imitation

1 code implementation6 Sep 2018 Shenda Hong, Cao Xiao, Trong Nghia Hoang, Tengfei Ma, Hongyan Li, Jimeng Sun

In many situations, we need to build and deploy separate models in related environments with different data qualities.

Knowledge Distillation

GAMENet: Graph Augmented MEmory Networks for Recommending Medication Combination

2 code implementations6 Sep 2018 Junyuan Shang, Cao Xiao, Tengfei Ma, Hongyan Li, Jimeng Sun

Recent progress in deep learning is revolutionizing the healthcare domain including providing solutions to medication recommendations, especially recommending medication combination for patients with complex health conditions.

Drug Similarity Integration Through Attentive Multi-view Graph Auto-Encoders

1 code implementation28 Apr 2018 Tengfei Ma, Cao Xiao, Jiayu Zhou, Fei Wang

In this paper, we propose to learn accurate and interpretable similarity measures from multiple types of drug features.

FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling

3 code implementations ICLR 2018 Jie Chen, Tengfei Ma, Cao Xiao

The graph convolutional networks (GCN) recently proposed by Kipf and Welling are an effective graph model for semi-supervised learning.

Node Classification

Multilingual Training of Crosslingual Word Embeddings

no code implementations EACL 2017 Long Duong, Hiroshi Kanayama, Tengfei Ma, Steven Bird, Trevor Cohn

Crosslingual word embeddings represent lexical items from different languages using the same vector space, enabling crosslingual transfer.

Bilingual Lexicon Induction Dependency Parsing +6

Inverted Bilingual Topic Models for Lexicon Extraction from Non-parallel Data

no code implementations21 Dec 2016 Tengfei Ma, Tetsuya Nasukawa

In this paper, we try to address two challenges of applying topic models to lexicon extraction in non-parallel data: 1) hard to model the word relationship and 2) noisy seed dictionary.

Topic Models Translation

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