scholarly journals Distributionally Robust Semi-Supervised Learning for People-Centric Sensing

2019 ◽  
Vol 33 ◽  
pp. 3321-3328 ◽  
Author(s):  
Kaixuan Chen ◽  
Lina Yao ◽  
Dalin Zhang ◽  
Xiaojun Chang ◽  
Guodong Long ◽  
...  
Keyword(s):  
Supervised Learning ◽  
State Of The Art ◽  
Behavior Patterns ◽  
Robust Model ◽  
Movement Recognition ◽  
Proposed Model ◽  
Latent Features ◽  
Real World Datasets ◽  
Distributionally Robust ◽  
And Behavior

Semi-supervised learning is crucial for alleviating labelling burdens in people-centric sensing. However, humangenerated data inherently suffer from distribution shift in semi-supervised learning due to the diverse biological conditions and behavior patterns of humans. To address this problem, we propose a generic distributionally robust model for semi-supervised learning on distributionally shifted data. Considering both the discrepancy and the consistency between the labeled data and the unlabeled data, we learn the latent features that reduce person-specific discrepancy and preserve task-specific consistency. We evaluate our model in a variety of people-centric recognition tasks on real-world datasets, including intention recognition, activity recognition, muscular movement recognition and gesture recognition. The experiment results demonstrate that the proposed model outperforms the state-of-the-art methods.

scholarly journals Multi-agent Attentional Activity Recognition

2019 ◽  
Author(s):  
Kaixuan Chen ◽  
Lina Yao ◽  
Dalin Zhang ◽  
Bin Guo ◽  
Zhiwen Yu
Keyword(s):  
Activity Recognition ◽  
State Of The Art ◽  
Body Part ◽  
Body Parts ◽  
Temporal Attention ◽  
Attention Model ◽  
Proposed Model ◽  
Collective Motions ◽  
Multi Agent ◽  
Real World Datasets

Multi-modality is an important feature of sensor based activity recognition. In this work, we consider two inherent characteristics of human activities, the spatially-temporally varying salience of features and the relations between activities and corresponding body part motions. Based on these, we propose a multi-agent spatial-temporal attention model. The spatial-temporal attention mechanism helps intelligently select informative modalities and their active periods. And the multiple agents in the proposed model represent activities with collective motions across body parts by independently selecting modalities associated with single motions. With a joint recognition goal, the agents share gained information and coordinate their selection policies to learn the optimal recognition model. The experimental results on four real-world datasets demonstrate that the proposed model outperforms the state-of-the-art methods.

scholarly journals MLRDA: A Multi-Task Semi-Supervised Learning Framework for Drug-Drug Interaction Prediction

2019 ◽  
Author(s):  
Xu Chu ◽  
Yang Lin ◽  
Yasha Wang ◽  
Leye Wang ◽  
Jiangtao Wang ◽  
...  
Keyword(s):  
Supervised Learning ◽  
State Of The Art ◽  
Multiple Drug ◽  
Prediction Methods ◽  
Learning Models ◽  
Preventable Hospitalizations ◽  
Interaction Prediction ◽  
Learning Framework ◽  
Task Learning ◽  
Real World Datasets

Drug-drug interactions (DDIs) are a major cause of preventable hospitalizations and deaths. Recently, researchers in the AI community try to improve DDI prediction in two directions, incorporating multiple drug features to better model the pharmacodynamics and adopting multi-task learning to exploit associations among DDI types. However, these two directions are challenging to reconcile due to the sparse nature of the DDI labels which inflates the risk of overfitting of multi-task learning models when incorporating multiple drug features. In this paper, we propose a multi-task semi-supervised learning framework MLRDA for DDI prediction. MLRDA effectively exploits information that is beneficial for DDI prediction in unlabeled drug data by leveraging a novel unsupervised disentangling loss CuXCov. The CuXCov loss cooperates with the classification loss to disentangle the DDI prediction relevant part from the irrelevant part in a representation learnt by an autoencoder, which helps to ease the difficulty in mining useful information for DDI prediction in both labeled and unlabeled drug data. Moreover, MLRDA adopts a multi-task learning framework to exploit associations among DDI types. Experimental results on real-world datasets demonstrate that MLRDA significantly outperforms state-of-the-art DDI prediction methods by up to 10.3% in AUPR.

scholarly journals Discrete Trust-aware Matrix Factorization for Fast Recommendation

2019 ◽  
Author(s):  
Guibing Guo ◽  
Enneng Yang ◽  
Li Shen ◽  
Xiaochun Yang ◽  
Xiaodong He
Keyword(s):  
Social Influence ◽  
Collaborative Filtering ◽  
Recommender Systems ◽  
Social Relations ◽  
Real World ◽  
Matrix Factorization ◽  
State Of The Art ◽  
Proposed Model ◽  
Hamming Space ◽  
Real World Datasets

Trust-aware recommender systems have received much attention recently for their abilities to capture the influence among connected users. However, they suffer from the efficiency issue due to large amount of data and time-consuming real-valued operations. Although existing discrete collaborative filtering may alleviate this issue to some extent, it is unable to accommodate social influence. In this paper we propose a discrete trust-aware matrix factorization (DTMF) model to take dual advantages of both social relations and discrete technique for fast recommendation. Specifically, we map the latent representation of users and items into a joint hamming space by recovering the rating and trust interactions between users and items. We adopt a sophisticated discrete coordinate descent (DCD) approach to optimize our proposed model. In addition, experiments on two real-world datasets demonstrate the superiority of our approach against other state-of-the-art approaches in terms of ranking accuracy and efficiency.

scholarly journals Multi-scale Information Diffusion Prediction with Reinforced Recurrent Networks

2019 ◽  
Author(s):  
Cheng Yang ◽  
Jian Tang ◽  
Maosong Sun ◽  
Ganqu Cui ◽  
Zhiyuan Liu
Keyword(s):  
Information Diffusion ◽  
State Of The Art ◽  
Sequential Data ◽  
Recurrent Networks ◽  
Multi Scale ◽  
Structural Context ◽  
Learning Techniques ◽  
Proposed Model ◽  
Real World Datasets ◽  
Diffusion Prediction

Information diffusion prediction is an important task which studies how information items spread among users. With the success of deep learning techniques, recurrent neural networks (RNNs) have shown their powerful capability in modeling information diffusion as sequential data. However, previous works focused on either microscopic diffusion prediction which aims at guessing the next influenced user or macroscopic diffusion prediction which estimates the total numbers of influenced users during the diffusion process. To the best of our knowledge, no previous works have suggested a unified model for both microscopic and macroscopic scales. In this paper, we propose a novel multi-scale diffusion prediction model based on reinforcement learning (RL). RL incorporates the macroscopic diffusion size information into the RNN-based microscopic diffusion model by addressing the non-differentiable problem. We also employ an effective structural context extraction strategy to utilize the underlying social graph information. Experimental results show that our proposed model outperforms state-of-the-art baseline models on both microscopic and macroscopic diffusion predictions on three real-world datasets.

scholarly journals Where to Go Next: Modeling Long- and Short-Term User Preferences for Point-of-Interest Recommendation

2020 ◽  
Vol 34 (01) ◽  
pp. 214-221 ◽  
Author(s):  
Ke Sun ◽  
Tieyun Qian ◽  
Tong Chen ◽  
Yile Liang ◽  
Quoc Viet Hung Nguyen ◽  
...  
Keyword(s):  
State Of The Art ◽  
User Preferences ◽  
Short Term ◽  
Preference Modeling ◽  
Point Of Interest ◽  
Proposed Model ◽  
Poi Recommendation ◽  
Novel Method ◽  
Real World Datasets

Point-of-Interest (POI) recommendation has been a trending research topic as it generates personalized suggestions on facilities for users from a large number of candidate venues. Since users' check-in records can be viewed as a long sequence, methods based on recurrent neural networks (RNNs) have recently shown promising applicability for this task. However, existing RNN-based methods either neglect users' long-term preferences or overlook the geographical relations among recently visited POIs when modeling users' short-term preferences, thus making the recommendation results unreliable. To address the above limitations, we propose a novel method named Long- and Short-Term Preference Modeling (LSTPM) for next-POI recommendation. In particular, the proposed model consists of a nonlocal network for long-term preference modeling and a geo-dilated RNN for short-term preference learning. Extensive experiments on two real-world datasets demonstrate that our model yields significant improvements over the state-of-the-art methods.

scholarly journals MNI: An enhanced multi-task neighborhood interaction model for recommendation on knowledge graph

PLoS ONE ◽  
2021 ◽  
Vol 16 (10) ◽  
pp. e0258410
Author(s):  
Xintao Ma ◽  
Liyan Dong ◽  
Yuequn Wang ◽  
Yongli Li ◽  
Hao Zhang
Keyword(s):  
Local Structure ◽  
Recommendation System ◽  
State Of The Art ◽  
Side Information ◽  
Interaction Model ◽  
Knowledge Graph ◽  
Graph Structure ◽  
Latent Features ◽  
Real World Datasets ◽  
Neighborhood Interaction

To alleviate the data sparsity and cold start problems for collaborative filtering in recommendation systems, side information is usually leveraged by researchers to improve the recommendation performance. The utility of knowledge graph regards the side information as part of the graph structure and gives an explanation for recommendation results. In this paper, we propose an enhanced multi-task neighborhood interaction (MNI) model for recommendation on knowledge graphs. MNI explores not only the user-item interaction but also the neighbor-neighbor interactions, capturing a more sophisticated local structure. Besides, the entities and relations are also semantically embedded. And with the cross&compress unit, items in the recommendation system and entities in the knowledge graph can share latent features, and thus high-order interactions can be investigated. Through extensive experiments on real-world datasets, we demonstrate that MNI outperforms some of the state-of-the-art baselines both for CTR prediction and top-N recommendation.

Follower Link Prediction using the XGBoostClassification Model with Multiple Graph Features

2021 ◽  
Author(s):  
Dayal Kumar Behera ◽  
Madhabananda Dash ◽  
Subhra Swetanisha ◽  
Janmenjoy Nayak ◽  
S Vimal ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Supervised Learning ◽  
Link Prediction ◽  
Prediction Models ◽  
Binary Classification ◽  
Prediction Problem ◽  
Global Features ◽  
Proposed Model ◽  
Real World Datasets

Abstract The Follower Link Prediction is an emerging application preferred by social networking sites to increase their user network. It helps in finding potential unseen individual and can be used for identifying relationship between nodes in social network. With the rapid growth of many users in social media, which users to follow leads to information overload problems. Previous works on link prediction problem are generally based on local and global features of a graph and limited to a smaller dataset. The number of users in social media is increasing in an extraordinary rate. Generating features for supervised learning from a large user network is challenging. In this paper, a supervised learning model (LPXGB) using XGBoost is proposed to consider the link prediction problem as a binary classification problem. Many hybrid graph feature techniques are used to represent the dataset suitable for machine learning. The efficiency of the LPXGB model is tested with three real world datasets Karate, Polblogs and Facebook. The proposed model is compared with various machine learning classifiers and also with traditional link prediction models. Experimental results are evident that the proposed model achieves higher classification accuracy and AUC value.

scholarly journals Aggregating Crowd Wisdoms with Label-aware Autoencoders

2017 ◽  
Author(s):  
Li'ang Yin ◽  
Jianhua Han ◽  
Weinan Zhang ◽  
Yong Yu
Keyword(s):  
Source Credibility ◽  
State Of The Art ◽  
Research Work ◽  
Generative Models ◽  
Majority Voting ◽  
Accuracy Improvement ◽  
Latent Features ◽  
Label Aggregation ◽  
Real World Datasets ◽  
Weighted Majority Voting

Aggregating crowd wisdoms takes multiple labels from various sources and infers true labels for objects. Recent research work makes progress by learning source credibility from data and roughly form three kinds of modeling frameworks: weighted majority voting, trust propagation, and generative models. In this paper, we propose a novel framework named Label-Aware Autoencoders (LAA) to aggregate crowd wisdoms. LAA integrates a classifier and a reconstructor into a unified model to infer labels in an unsupervised manner. Analogizing classical autoencoders, we can regard the classifier as an encoder, the reconstructor as a decoder, and inferred labels as latent features. To the best of our knowledge, it is the first trial to combine label aggregation with autoencoders. We adopt networks to implement the classifier and the reconstructor which have the potential to automatically learn underlying patterns of source credibility. To further improve inference accuracy, we introduce object ambiguity and latent aspects into LAA. Experiments on three real-world datasets show that proposed models achieve impressive inference accuracy improvement over state-of-the-art models.

scholarly journals DSINE: Deep Structural Influence Learning via Network Embedding

2019 ◽  
Vol 33 ◽  
pp. 10065-10066 ◽  
Author(s):  
Jianjun Wu ◽  
Ying Sha ◽  
Bo Jiang ◽  
Jianlong Tan
Keyword(s):  
Social Influence ◽  
Real World ◽  
Local Structure ◽  
State Of The Art ◽  
Viral Marketing ◽  
Network Embedding ◽  
Proposed Model ◽  
Real World Datasets ◽  
Global And Local ◽  
Structural Influence

Structural representations of user social influence are critical for a variety of applications such as viral marketing and recommendation products. However, existing studies only focus on capturing and preserving the structure of relations, and ignore the diversity of influence relations patterns among users. To this end, we propose a deep structural influence learning model to learn social influence structure via mining rich features of each user, and fuse information from the aligned selfnetwork component for preserving global and local structure of the influence relations among users. Experiments on two real-world datasets demonstrate that the proposed model outperforms the state-of-the-art algorithms for learning rich representations in multi-label classification task.

scholarly journals Understanding Users' Budgets for Recommendation with Hierarchical Poisson Factorization

2017 ◽  
Author(s):  
Yunhui Guo ◽  
Congfu Xu ◽  
Hanzhang Song ◽  
Xin Wang
Keyword(s):  
Recommender Systems ◽  
Real World ◽  
Online Shopping ◽  
State Of The Art ◽  
Generative Model ◽  
Personal Consumption ◽  
Proposed Model ◽  
Recommendation Algorithms ◽  
Real World Datasets ◽  
Consumption Habits

People consume and rate products in online shopping websites. The historical purchases of customers reflect their personal consumption habits and indicate their future shopping behaviors. Traditional preference-based recommender systems try to provide recommendations by analyzing users' feedback such as ratings and clicks. But unfortunately, most of the existing recommendation algorithms ignore the budget of the users. So they cannot avoid recommending users with products that will exceed their budgets. And they also cannot understand how the users will assign their budgets to different products. In this paper, we develop a generative model named collaborative budget-aware Poisson factorization (CBPF) to connect users' ratings and budgets. The CBPF model is intuitive and highly interpretable. We compare the proposed model with several state-of-the-art budget-unaware recommendation methods on several real-world datasets. The results show the advantage of uncovering users' budgets for recommendation.

Sign in / Sign up

Export Citation Format

Share Document