scholarly journals Multi-Agent Actor-Critic with Hierarchical Graph Attention Network

2020 ◽  
Vol 34 (05) ◽  
pp. 7236-7243
Author(s):  
Heechang Ryu ◽  
Hayong Shin ◽  
Jinkyoo Park
Keyword(s):  
Representation Learning ◽  
Policy Learning ◽  
Group Level ◽  
Multiple Agents ◽  
Attention Network ◽  
Attention Networks ◽  
Hierarchical Graph ◽  
Proposed Model ◽  
Multi Agent ◽  
Strategic Policies

Most previous studies on multi-agent reinforcement learning focus on deriving decentralized and cooperative policies to maximize a common reward and rarely consider the transferability of trained policies to new tasks. This prevents such policies from being applied to more complex multi-agent tasks. To resolve these limitations, we propose a model that conducts both representation learning for multiple agents using hierarchical graph attention network and policy learning using multi-agent actor-critic. The hierarchical graph attention network is specially designed to model the hierarchical relationships among multiple agents that either cooperate or compete with each other to derive more advanced strategic policies. Two attention networks, the inter-agent and inter-group attention layers, are used to effectively model individual and group level interactions, respectively. The two attention networks have been proven to facilitate the transfer of learned policies to new tasks with different agent compositions and allow one to interpret the learned strategies. Empirically, we demonstrate that the proposed model outperforms existing methods in several mixed cooperative and competitive tasks.

scholarly journals Multi-View Deep Attention Network for Reinforcement Learning (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13811-13812
Author(s):  
Yueyue Hu ◽  
Shiliang Sun ◽  
Xin Xu ◽  
Jing Zhao
Keyword(s):  
Reinforcement Learning ◽  
Single Agent ◽  
Representation Learning ◽  
Learning Task ◽  
Comprehensive Strategy ◽  
Attention Network ◽  
Single View ◽  
Learning Agents ◽  
Proposed Model ◽  
First Time

The representation approximated by a single deep network is usually limited for reinforcement learning agents. We propose a novel multi-view deep attention network (MvDAN), which introduces multi-view representation learning into the reinforcement learning task for the first time. The proposed model approximates a set of strategies from multiple representations and combines these strategies based on attention mechanisms to provide a comprehensive strategy for a single-agent. Experimental results on eight Atari video games show that the MvDAN has effective competitive performance than single-view reinforcement learning methods.

scholarly journals SAEP: A Surrounding-Aware Individual Emotion Prediction Model Combined with T-LSTM and Memory Attention Mechanism

2021 ◽  
Vol 11 (23) ◽  
pp. 11111
Author(s):  
Yakun Wang ◽  
Yajun Du ◽  
Jinrong Hu ◽  
Xianyong Li ◽  
Xiaoliang Chen
Keyword(s):  
Prediction Model ◽  
Alternative Methods ◽  
Attention Network ◽  
Attention Networks ◽  
Proposed Model ◽  
Decoder Architecture ◽  
Novel Variant ◽  
Emotional Changes ◽  
Evolving Context

The future emotion prediction of users on social media has been attracting increasing attention from academics. Previous studies on predicting future emotion have focused on the characteristics of individuals’ emotion changes; however, the role of the individual’s neighbors has not yet been thoroughly researched. To fill this gap, a surrounding-aware individual emotion prediction model (SAEP) based on a deep encoder–decoder architecture is proposed to predict individuals’ future emotions. In particular, two memory-based attention networks are constructed: The time-evolving attention network and the surrounding attention network to extract the features of the emotional changes of users and neighbors, respectively. Then, these features are incorporated into the emotion prediction task. In addition, a novel variant LSTM is introduced as the encoder of the proposed model, which can effectively extract complex patterns of users’ emotional changes from irregular time series. Extensive experimental results show that the proposed approach outperforms five alternative methods. The SAEP approach has improved by approximately 4.21–14.84% micro F1 on a dataset built from Twitter and 7.30–13.41% on a dataset built from Microblog. Further analyses validate the effectiveness of the proposed time-evolving context and surrounding context, as well as the factors that may affect the prediction results.

scholarly journals Recipe Recommendation With Hierarchical Graph Attention Network

2022 ◽  
Vol 4 ◽  
Author(s):  
Yijun Tian ◽  
Chuxu Zhang ◽  
Ronald Metoyer ◽  
Nitesh V. Chawla
Keyword(s):  
Neural Network ◽  
Eating Habits ◽  
Learning Approach ◽  
Attention Network ◽  
Relational Information ◽  
Food Items ◽  
Hierarchical Graph ◽  
Proposed Model ◽  
Network Modules ◽  
User History

Recipe recommendation systems play an important role in helping people find recipes that are of their interest and fit their eating habits. Unlike what has been developed for recommending recipes using content-based or collaborative filtering approaches, the relational information among users, recipes, and food items is less explored. In this paper, we leverage the relational information into recipe recommendation and propose a graph learning approach to solve it. In particular, we propose HGAT, a novel hierarchical graph attention network for recipe recommendation. The proposed model can capture user history behavior, recipe content, and relational information through several neural network modules, including type-specific transformation, node-level attention, and relation-level attention. We further introduce a ranking-based objective function to optimize the model. Thorough experiments demonstrate that HGAT outperforms numerous baseline methods.

scholarly journals A Multi-Attention Network for Aspect-Level Sentiment Analysis

2019 ◽  
Vol 11 (7) ◽  
pp. 157 ◽  
Author(s):  
Qiuyue Zhang ◽  
Ran Lu
Keyword(s):  
Neural Networks ◽  
Sentiment Analysis ◽  
Specific Aspect ◽  
Experimental Results ◽  
Sequence Information ◽  
Attention Network ◽  
Attention Networks ◽  
Recent Advances ◽  
Proposed Model ◽  
The Impact

Aspect-level sentiment analysis (ASA) aims at determining the sentiment polarity of specific aspect term with a given sentence. Recent advances in attention mechanisms suggest that attention models are useful in ASA tasks and can help identify focus words. Or combining attention mechanisms with neural networks are also common methods. However, according to the latest research, they often fail to extract text representations efficiently and to achieve interaction between aspect terms and contexts. In order to solve the complete task of ASA, this paper proposes a Multi-Attention Network (MAN) model which adopts several attention networks. This model not only preprocesses data by Bidirectional Encoder Representations from Transformers (BERT), but a number of measures have been taken. First, the MAN model utilizes the partial Transformer after transformation to obtain hidden sequence information. Second, because words in different location have different effects on aspect terms, we introduce location encoding to analyze the impact on distance from ASA tasks, then we obtain the influence of different words with aspect terms through the bidirectional attention network. From the experimental results of three datasets, we could find that the proposed model could achieve consistently superior results.

Towards Spike based Models of Visual Attention in the Brain

2015 ◽  
Vol 6 (2) ◽  
pp. 117-138
Author(s):  
Terje Kristensen
Keyword(s):  
Visual Attention ◽  
Communication Model ◽  
Attention Network ◽  
Attention Networks ◽  
Multi Agent ◽  
Biological Neuron ◽  
The Moment ◽  
Attention Systems ◽  
The Brain

A numerical solution of Hodgkin Huxley equations is presented to simulate the spiking behavior of a biological neuron. The solution is illustrated by building a graphical chart interface to finely tune the behavior of the neuron under different stimulations. In addition, a Multi-Agent System (MAS) has been developed to simulate the Visual Attention Network Model of the brain. Tasks are assigned to the agents according to the Attention Network Theory, developed by neuroscientists. A sequential communication model based on simple objects has been constructed, aiming to show the relations and the workflow between the different visual attention networks. Each agent is being used as an analogy to a role or function of the visual attention systems in the brain. Some experimental results based on this model have been presented in an earlier paper. The two approaches are at the moment not integrated. The long term goal is to develop an integrated parallel layered object model of the visual attention process, as a tool for simulating neuron interactions described by Hodgkin Huxley's equations or the Leaky-Integrate-and-Fire model.

W-MMP2Vec: Topic-driven network embedding model for link prediction in content-based heterogeneous information network

2021 ◽  
Vol 25 (3) ◽  
pp. 711-738
Author(s):  
Phu Pham ◽  
Phuc Do
Keyword(s):  
Link Prediction ◽  
Representation Learning ◽  
Information Network ◽  
Network Embedding ◽  
Heterogeneous Information Network ◽  
Heterogeneous Information ◽  
Learning Framework ◽  
Novel Approach ◽  
Proposed Model ◽  
Meta Path

Link prediction on heterogeneous information network (HIN) is considered as a challenge problem due to the complexity and diversity in types of nodes and links. Currently, there are remained challenges of meta-path-based link prediction in HIN. Previous works of link prediction in HIN via network embedding approach are mainly focused on exploiting features of node rather than existing relations in forms of meta-paths between nodes. In fact, predicting the existence of new links between non-linked nodes is absolutely inconvincible. Moreover, recent HIN-based embedding models also lack of thorough evaluations on the topic similarity between text-based nodes along given meta-paths. To tackle these challenges, in this paper, we proposed a novel approach of topic-driven multiple meta-path-based HIN representation learning framework, namely W-MMP2Vec. Our model leverages the quality of node representations by combining multiple meta-paths as well as calculating the topic similarity weight for each meta-path during the processes of network embedding learning in content-based HINs. To validate our approach, we apply W-TMP2Vec model in solving several link prediction tasks in both content-based and non-content-based HINs (DBLP, IMDB and BlogCatalog). The experimental outputs demonstrate the effectiveness of proposed model which outperforms recent state-of-the-art HIN representation learning models.

scholarly journals Social exclusion increases the executive function of attention networks

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Huoyin Zhang ◽  
Shiyunmeng Zhang ◽  
Jiachen Lu ◽  
Yi Lei ◽  
Hong Li
Keyword(s):  
Social Exclusion ◽  
Executive Control ◽  
Brain Regions ◽  
Negative Influence ◽  
Future Research ◽  
Research Attention ◽  
Attention Network ◽  
Attention Networks ◽  
The Social ◽  
And Control

AbstractPrevious studies in humans have shown that brain regions activating social exclusion overlap with those related to attention. However, in the context of social exclusion, how does behavioral monitoring affect individual behavior? In this study, we used the Cyberball game to induce the social exclusion effect in a group of participants. To explore the influence of social exclusion on the attention network, we administered the Attention Network Test (ANT) and compared results for the three subsystems of the attention network (orienting, alerting, and executive control) between exclusion (N = 60) and inclusion (N = 60) groups. Compared with the inclusion group, the exclusion group showed shorter overall response time and better executive control performance, but no significant differences in orienting or alerting. The excluded individuals showed a stronger ability to detect and control conflicts. It appears that social exclusion does not always exert a negative influence on individuals. In future research, attention to network can be used as indicators of social exclusion. This may further reveal how social exclusion affects individuals' psychosomatic mechanisms.

scholarly journals Graph contextualized attention network for predicting synthetic lethality in human cancers

2021 ◽  
Author(s):  
Yahui Long ◽  
Min Wu ◽  
Yong Liu ◽  
Jie Zheng ◽  
Chee Keong Kwoh ◽  
...  
Keyword(s):  
Synthetic Lethality ◽  
Critical Role ◽  
Design Feature ◽  
Cost Effective ◽  
Attention Network ◽  
New Genes ◽  
Lab Experiments ◽  
Proposed Model ◽  
Multiple Feature ◽  
Wet Lab

Abstract Motivation Synthetic Lethality (SL) plays an increasingly critical role in the targeted anticancer therapeutics. In addition, identifying SL interactions can create opportunities to selectively kill cancer cells without harming normal cells. Given the high cost of wet-lab experiments, in silico prediction of SL interactions as an alternative can be a rapid and cost-effective way to guide the experimental screening of candidate SL pairs. Several matrix factorization-based methods have recently been proposed for human SL prediction. However, they are limited in capturing the dependencies of neighbors. In addition, it is also highly challenging to make accurate predictions for new genes without any known SL partners. Results In this work, we propose a novel graph contextualized attention network named GCATSL to learn gene representations for SL prediction. First, we leverage different data sources to construct multiple feature graphs for genes, which serve as the feature inputs for our GCATSL method. Second, for each feature graph, we design node-level attention mechanism to effectively capture the importance of local and global neighbors and learn local and global representations for the nodes, respectively. We further exploit multi-layer perceptron (MLP) to aggregate the original features with the local and global representations and then derive the feature-specific representations. Third, to derive the final representations, we design feature-level attention to integrate feature-specific representations by taking the importance of different feature graphs into account. Extensive experimental results on three datasets under different settings demonstrated that our GCATSL model outperforms 14 state-of-the-art methods consistently. In addition, case studies further validated the effectiveness of our proposed model in identifying novel SL pairs. Availability Python codes and dataset are freely available on GitHub (https://github.com/longyahui/GCATSL) and Zenodo (https://zenodo.org/record/4522679) under the MIT license.

An E2GPGP-GASA-Based Multi-Agent Job Shop Scheduling System

2012 ◽  
Vol 505 ◽  
pp. 65-74
Author(s):  
Lin Lin Lu ◽  
Xin Ma ◽  
Ya Xuan Wang
Keyword(s):  
Large Scale ◽  
Job Shop ◽  
Job Shop Scheduling ◽  
Simulation Software ◽  
Prototype System ◽  
Shop Scheduling ◽  
Model Combining ◽  
Proposed Model ◽  
Multi Agent ◽  
Global Planning

In this paper, a job shop scheduling model combining MAS (Multi-Agent System) with GASA (Simulated Annealing-Genetic Algorithm) is presented. The proposed model is based on the E2GPGP (extended extended generalized partial global planning) mechanism and utilizes the advantages of static intelligence algorithms with dynamic MAS. A scheduling process from ‘initialized macro-scheduling’ to ‘repeated micro-scheduling’ is designed for large-scale complex problems to enable to implement an effective and widely applicable prototype system for the job shop scheduling problem (JSSP). Under a set of theoretic strategies in the GPGP which is summarized in detail, E2GPGP is also proposed further. The GPGP-cooperation-mechanism is simulated by using simulation software DECAF for the JSSP. The results show that the proposed model based on the E2GPGP-GASA not only improves the effectiveness, but also reduces the resource cost.

Sign in / Sign up

Export Citation Format

Share Document