384 Hits in 3.0 sec


Ralitsa Angelova, Gjergji Kasneci, Fabian M. Suchanek, Gerhard Weikum
2009 Proceedings of the 18th international conference on World wide web - WWW '09  
We present a graph-based approach which models the mutual influence between nodes in the network as a random walk.  ...  We introduce a multi-label classification model and algorithm for labeling heterogeneous networks, where nodes belong to different types and different types have different sets of classification labels  ...  Therefore, graph-based classification methods, designed to derive class labels based on direct links between the graph nodes will degrade in their performance, because most direct links connect different  ... 
doi:10.1145/1526709.1526869 dblp:conf/www/AngelovaKSW09 fatcat:ry2whxmtxbaaljuvmf7adc4xuy

Guest editorial: content, concept and context mining in social media

Heng Tao Shen, Xian-Sheng Hua, Jiebo Luo, Vincent Oria
2011 World wide web (Bussum)  
., titled "Graffiti: Graph-based Classification in Heterogeneous Networks", addresses the problem of multi-label classification in heterogeneous graphs representing the social data on the Web and proposes  ...  The results reveal that the influence of interest-based homophily is not a very strong leading factor for constructing new ties in social media sites.  ... 
doi:10.1007/s11280-011-0142-4 fatcat:lzq4xr5lwzecjdtikt3kbc7sjm

Multimodal Classification of Urban Micro-Events

Maarten Sukel, Stevan Rudinac, Marcel Worring
2019 Proceedings of the 27th ACM International Conference on Multimedia - MM '19  
We evaluate performance in terms of accurate classification of urban micro-events on a real world dataset obtained from a live citizen reporting system.  ...  In this paper we explore several methods of creating such a classifier, including early, late and hybrid fusion as well as representation learning using multimodal graphs.  ...  CONCLUSION In this paper we investigated the potential for automatically classifying urban micro events based on heterogeneous information describing them in citizen reports, which ranges from text and  ... 
doi:10.1145/3343031.3350967 dblp:conf/mm/SukelRW19 fatcat:6wxrqhtkgzh65piariyky6uxle

Labeling Actors in Social Networks Using a Heterogeneous Graph Kernel [chapter]

Ngot Bui, Vasant Honavar
2014 Lecture Notes in Computer Science  
We show that the resulting heterogeneous graph kernel (HGK) can be used to build accurate classifiers for labeling actors in social networks.  ...  We introduce a variant of the random walk graph kernel to deal with the heterogeneous nature of the network (i.e., presence of a large number of node and link types).  ...  RankClass and Graffiti offer probabilistic models for labeling actors in heterogeneous social networks.  ... 
doi:10.1007/978-3-319-05579-4_4 fatcat:s7fcpyn32jhbfgevmbxxd6hsrm

Learning latent representations of nodes for classifying in heterogeneous social networks

Yann Jacob, Ludovic Denoyer, Patrick Gallinari
2014 Proceedings of the 7th ACM international conference on Web search and data mining - WSDM '14  
We address here the specific problem of nodes classification and tagging in heterogeneous social networks, where different types of nodes are considered, each type with its own label or tag set.  ...  Inference is then performed in this latent space. In this framework, two nodes connected in the network will tend to share similar representations regardless of their types.  ...  Classification in heterogeneous networks, representative of real world media, is much more recent with only a few attempts for now.  ... 
doi:10.1145/2556195.2556225 dblp:conf/wsdm/JacobDG14 fatcat:klpzid4d5nferl35fpk5wobkxe

Multimodal Classification of Urban Micro-Events [article]

Maarten Sukel, Stevan Rudinac, Marcel Worring
2019 arXiv   pre-print
In this paper we explore several methods of creating such a classifier, including early, late, hybrid fusion and representation learning using multimodal graphs.  ...  Furthermore, we demonstrate that our hybrid combination of early and late fusion with multimodal embeddings performs best in classification of urban micro-events.  ...  CONCLUSION In this paper we investigated the potential for automatically classifying urban micro events based on heterogeneous information describing them in citizen reports, which ranges from text and  ... 
arXiv:1904.13349v1 fatcat:ktrupj4aeraanncrabziuay4q4

A Survey of Data Mining Techniques on Information Networks

Sadhana Kodali, Madhavi Dabbiru, B Thirumala Rao
2018 International Journal of Engineering & Technology  
The Data Mining techniques of both homogeneous and heterogeneous information networks are discussed in detail and a comparative study on each problem category is showcased.  ...  In our day-to-day life we can find these information networks like the social media network, the network formed by the interaction of web objects etc.  ...  This approach is a graph based classification and is applicable for heterogeneous networks.  ... 
doi:10.14419/ijet.v7i2.6.11267 fatcat:zavu7rli4ja2ne3nj6wiz4wxhi

On the utility of abstraction in labeling actors in social networks

Ngot Bui, Vasant Honavar
2013 Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining - ASONAM '13  
In this paper, we consider the task of assigning labels to the unlabeled actors (individuals) in a large heterogeneous social network in which labels are available for a subset of actors.  ...  Specifically, we seek to learn a predictive model to label actors based on the attributes of the actors themselves and/or items that are linked to them in the network.  ...  This research was funded in part by an NSF grant IIS 0711356. The work of Vasant Honavar while working at the National Science Foundation, was supported by the Foundation.  ... 
doi:10.1145/2492517.2492607 dblp:conf/asunam/BuiH13 fatcat:qofn3xhhlrbbziiy56xv4r47mq

Hashtag Recommendation Methods for Twitter and Sina Weibo: A Review

Areej Alsini, Du Q. Huynh, Amitava Datta
2021 Future Internet  
Taking this perspective, we present a taxonomy of hashtag recommendation based on the research methodologies that have been used. We provide a critical review of each of the classes in the taxonomy.  ...  We also discuss the challenges remaining in the field and outline future research directions in this area of study.  ...  [57] built the HE-graph, a heterogeneous graph of hashtags and Wikipedia terms drawn from tweets.  ... 
doi:10.3390/fi13050129 fatcat:6mn6h53g6fg4ro44l24m4uhv3u

Neuro-Symbolic Learning: Principles and Applications in Ophthalmology [article]

Muhammad Hassan, Haifei Guan, Aikaterini Melliou, Yuqi Wang, Qianhui Sun, Sen Zeng, Wen Liang, Yiwei Zhang, Ziheng Zhang, Qiuyue Hu, Yang Liu, Shunkai Shi (+15 others)
2022 arXiv   pre-print
Neural networks have been rapidly expanding in recent years, with novel strategies and applications.  ...  Attempts have been made to overcome the challenges in neural network computing by representing and embedding domain knowledge in terms of symbolic representations.  ...  The inclusion of heterogeneous graph based networks may overcome the challenges of fairness in the treatment of complex relationships and interpretability [143] .  ... 
arXiv:2208.00374v1 fatcat:pktmnomj3bbwpjyj7lmu37rl7i

A Survey on Machine Learning Techniques for Auto Labeling of Video, Audio, and Text Data [article]

Shikun Zhang, Omid Jafari, Parth Nagarkar
2021 arXiv   pre-print
Machine learning has been utilized to perform tasks in many different domains such as classification, object detection, image segmentation and natural language analysis.  ...  Data labeling has always been one of the most important tasks in machine learning. However, labeling large amounts of data increases the monetary cost in machine learning.  ...  In order to solve the multi-label classification problem, authors propose a novel convolutional clustering neural network (CCNN).  ... 
arXiv:2109.03784v1 fatcat:uu55zfmtajcvdjekxeaue76izy

Predicting and Understanding Urban Perception with Convolutional Neural Networks

Lorenzo Porzi, Samuel Rota Bulò, Bruno Lepri, Elisa Ricci
2015 Proceedings of the 23rd ACM international conference on Multimedia - MM '15  
Cities' visual appearance plays a central role in shaping human perception and response to the surrounding urban environment.  ...  In this paper we propose a novel approach for predicting the perceived safety of a scene from Google Street View Images.  ...  to obtain an acyclic graph.  ... 
doi:10.1145/2733373.2806273 dblp:conf/mm/PorziBLR15 fatcat:amyy7zusfbhadfmc7pytnxa7ga

A survey of Big Data dimensions vs Social Networks analysis

Michele Ianni, Elio Masciari, Giancarlo Sperlí
2020 Journal of Intelligent Information Systems  
The pervasive diffusion of Social Networks (SN) produced an unprecedented amount of heterogeneous data.  ...  More in detail, the analysis of user generated data by popular social networks (i.e Facebook (, Twitter (, Instagram (, LinkedIn  ...  graphs.  ... 
doi:10.1007/s10844-020-00629-2 pmid:33191981 pmcid:PMC7649712 fatcat:3hvd5sshwzd67lxi4qlo2sgnwe

Size-Invariant Graph Representations for Graph Classification Extrapolations [article]

Beatrice Bevilacqua, Yangze Zhou, Bruno Ribeiro
2021 arXiv   pre-print
In this work we consider an underexplored area of an otherwise rapidly developing field of graph representation learning: The task of out-of-distribution (OOD) graph classification, where train and test  ...  In general, graph representation learning methods assume that the train and test data come from the same distribution.  ...  Andrews Fellowship, and the Wabash Heartland Innovation Network.  ... 
arXiv:2103.05045v2 fatcat:yul2sfauanhjfppdvdqz4vanme

Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images [article]

Lei Sun, Kailun Yang, Xinxin Hu, Weijian Hu, Kaiwei Wang
2020 arXiv   pre-print
In this paper, we propose a real-time fusion semantic segmentation network termed RFNet that effectively exploits complementary cross-modal information.  ...  Semantic segmentation has made striking progress due to the success of deep convolutional neural networks.  ...  Bar graph 6 shows that RFNet performs better in all depth ranges in the case of mean IoU of 20 classes.  ... 
arXiv:2002.10570v2 fatcat:tfnxpu5mxbclla5icoe25vwys4
« Previous Showing results 1 — 15 out of 384 results