scholarly journals Learning Multi-Task Communication with Message Passing for Sequence Learning

2019 ◽  
Vol 33 ◽  
pp. 4360-4367 ◽  
Author(s):  
Pengfei Liu ◽  
Jie Fu ◽  
Yue Dong ◽  
Xipeng Qiu ◽  
Jackie Chi Kit Cheung
Keyword(s):  
Neural Networks ◽  
Transfer Learning ◽  
Text Classification ◽  
Sequence Learning ◽  
Message Passing ◽  
Ad Hoc ◽  
General Graph ◽  
Learning Framework ◽  
Task Learning ◽  
Graph Neural Networks

We present two architectures for multi-task learning with neural sequence models. Our approach allows the relationships between different tasks to be learned dynamically, rather than using an ad-hoc pre-defined structure as in previous work. We adopt the idea from message-passing graph neural networks, and propose a general graph multi-task learning framework in which different tasks can communicate with each other in an effective and interpretable way. We conduct extensive experiments in text classification and sequence labelling to evaluate our approach on multi-task learning and transfer learning. The empirical results show that our models not only outperform competitive baselines, but also learn interpretable and transferable patterns across tasks.

scholarly journals Message Passing Attention Networks for Document Understanding

2020 ◽  
Vol 34 (05) ◽  
pp. 8544-8551 ◽  
Author(s):  
Giannis Nikolentzos ◽  
Antoine Tixier ◽  
Michalis Vazirgiannis
Keyword(s):  
Neural Networks ◽  
Text Classification ◽  
Message Passing ◽  
State Of The Art ◽  
Structured Data ◽  
Attention Networks ◽  
Document Understanding ◽  
Standard Text ◽  
Graph Neural Networks ◽  
The Impact

Graph neural networks have recently emerged as a very effective framework for processing graph-structured data. These models have achieved state-of-the-art performance in many tasks. Most graph neural networks can be described in terms of message passing, vertex update, and readout functions. In this paper, we represent documents as word co-occurrence networks and propose an application of the message passing framework to NLP, the Message Passing Attention network for Document understanding (MPAD). We also propose several hierarchical variants of MPAD. Experiments conducted on 10 standard text classification datasets show that our architectures are competitive with the state-of-the-art. Ablation studies reveal further insights about the impact of the different components on performance. Code is publicly available at: https://github.com/giannisnik/mpad.

scholarly journals Contextualized Non-Local Neural Networks for Sequence Learning

2019 ◽  
Vol 33 ◽  
pp. 6762-6769 ◽  
Author(s):  
Pengfei Liu ◽  
Shuaichen Chang ◽  
Xuanjing Huang ◽  
Jian Tang ◽  
Jackie Chi Kit Cheung
Keyword(s):  
Neural Networks ◽  
Text Classification ◽  
Sequence Learning ◽  
Neural Mechanisms ◽  
Semantic Matching ◽  
Proposed Model ◽  
Non Local ◽  
Graph Neural Networks ◽  
Transformer Model ◽  
Dependency Structures

Recently, a large number of neural mechanisms and models have been proposed for sequence learning, of which selfattention, as exemplified by the Transformer model, and graph neural networks (GNNs) have attracted much attention. In this paper, we propose an approach that combines and draws on the complementary strengths of these two methods. Specifically, we propose contextualized non-local neural networks (CN3), which can both dynamically construct a task-specific structure of a sentence and leverage rich local dependencies within a particular neighbourhood.Experimental results on ten NLP tasks in text classification, semantic matching, and sequence labelling show that our proposed model outperforms competitive baselines and discovers task-specific dependency structures, thus providing better interpretability to users.

scholarly journals Coloring Graph Neural Networks for Node Disambiguation

2020 ◽  
Author(s):  
George Dasoulas ◽  
Ludovic Dos Santos ◽  
Kevin Scaman ◽  
Aladin Virmaux
Keyword(s):  
Neural Networks ◽  
Message Passing ◽  
State Of The Art ◽  
Structural Characteristics ◽  
Expressive Power ◽  
Continuous Functions ◽  
Graph Classification ◽  
Node Attributes ◽  
Graph Neural Networks ◽  
Coloring Graph

In this paper, we show that a simple coloring scheme can improve, both theoretically and empirically, the expressive power of Message Passing Neural Networks (MPNNs). More specifically, we introduce a graph neural network called Colored Local Iterative Procedure (CLIP) that uses colors to disambiguate identical node attributes, and show that this representation is a universal approximator of continuous functions on graphs with node attributes. Our method relies on separability, a key topological characteristic that allows to extend well-chosen neural networks into universal representations. Finally, we show experimentally that CLIP is capable of capturing structural characteristics that traditional MPNNs fail to distinguish, while being state-of-the-art on benchmark graph classification datasets.

scholarly journals Multi-Task Learning for Metaphor Detection with Graph Convolutional Neural Networks and Word Sense Disambiguation

2020 ◽  
Vol 34 (05) ◽  
pp. 8139-8146
Author(s):  
Duong Le ◽  
My Thai ◽  
Thien Nguyen
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Word Sense Disambiguation ◽  
Word Sense ◽  
Knowledge Resources ◽  
Useful Knowledge ◽  
Learning Framework ◽  
Task Learning ◽  
Sense Disambiguation

The current deep learning works on metaphor detection have only considered this task independently, ignoring the useful knowledge from the related tasks and knowledge resources. In this work, we introduce two novel mechanisms to improve the performance of the deep learning models for metaphor detection. The first mechanism employs graph convolutional neural networks (GCN) with dependency parse trees to directly connect the words of interest with their important context words for metaphor detection. The GCN networks in this work also present a novel control mechanism to filter the learned representation vectors to retain the most important information for metaphor detection. The second mechanism, on the other hand, features a multi-task learning framework that exploits the similarity between word sense disambiguation and metaphor detection to transfer the knowledge between the two tasks. The extensive experiments demonstrate the effectiveness of the proposed techniques, yielding the state-of-the-art performance over several datasets.

scholarly journals Deep Attention Diffusion Graph Neural Networks for Text Classification

2021 ◽  
Author(s):  
Yonghao Liu ◽  
Renchu Guan ◽  
Fausto Giunchiglia ◽  
Yanchun Liang ◽  
Xiaoyue Feng
Keyword(s):  
Neural Networks ◽  
Text Classification ◽  
Graph Neural Networks

scholarly journals Performance Evaluation of Caps-Net Based Multitask Learning Architecture for Text Classification

2020 ◽  
Vol 2 (1) ◽  
pp. 1-10 ◽  
Author(s):  
Dr. I. Jeena Jacob
Keyword(s):  
Neural Networks ◽  
Performance Evaluation ◽  
Image Classification ◽  
Text Classification ◽  
Multitask Learning ◽  
Learning Capability ◽  
Task Learning ◽  
Multiple Tasks ◽  
Frame Work

The classification of the text involving the process of identification and categorization of text is a tedious and a challenging task too. The Capsules Network (Caps-Net) which is a unique architecture with the capability to confiscate the basic attributes comprising the insights of the particular field that could help in bridging the knowledge gap existing between the source and the destination tasks and capability learn more robust representation than the CNN-Convolutional neural networks in the image classification domain is utilized in the paper to classify the text. As the multi –task learning capability enables to part insights between the tasks that are related and enhances data used in training indirectly, the Caps-Net based multi task learning frame work is proposed in the paper. The proposed architecture including the Caps-Net effectively classifies the text and minimizes the interference experienced among the multiple tasks in the multi –task learning. The architecture put forward is evaluated using various text classification dataset ensuring the efficacy of the proffered frame work

scholarly journals UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks

2021 ◽  
Author(s):  
Jing Huang ◽  
Jie Yang
Keyword(s):  
Neural Networks ◽  
Message Passing ◽  
State Of The Art ◽  
Representation Learning ◽  
Graph Representation ◽  
Challenging Problem ◽  
Unified Framework ◽  
Real World Datasets ◽  
Graph Neural Networks ◽  
Research Domains

Hypergraph, an expressive structure with flexibility to model the higher-order correlations among entities, has recently attracted increasing attention from various research domains. Despite the success of Graph Neural Networks (GNNs) for graph representation learning, how to adapt the powerful GNN-variants directly into hypergraphs remains a challenging problem. In this paper, we propose UniGNN, a unified framework for interpreting the message passing process in graph and hypergraph neural networks, which can generalize general GNN models into hypergraphs. In this framework, meticulously-designed architectures aiming to deepen GNNs can also be incorporated into hypergraphs with the least effort. Extensive experiments have been conducted to demonstrate the effectiveness of UniGNN on multiple real-world datasets, which outperform the state-of-the-art approaches with a large margin. Especially for the DBLP dataset, we increase the accuracy from 77.4% to 88.8% in the semi-supervised hypernode classification task. We further prove that the proposed message-passing based UniGNN models are at most as powerful as the 1-dimensional Generalized Weisfeiler-Leman (1-GWL) algorithm in terms of distinguishing non-isomorphic hypergraphs. Our code is available at https://github.com/OneForward/UniGNN.

Sign in / Sign up

Export Citation Format

Share Document