Relational learning via latent social dimensions
Abstract
Social media such as blogs, Facebook, Flickr, etc., presents data in a network format rather than classical IID distribution. To address the interdependency among data instances, relational learning has been proposed, and collective inference based on network connectivity is adopted for prediction. However, connections in social media are often multi-dimensional. An actor can connect to another actor for different reasons, e.g., alumni, colleagues, living in the same city, sharing similar interests, etc. Collective inference normally does not differentiate these connections. In this work, we propose to extract latent social dimensions based on network information, and then utilize them as features for discriminative learning. These social dimensions describe diverse affiliations of actors hidden in the network, and the discriminative learning can automatically determine which affiliations are better aligned with the class labels. Such a scheme is preferred when multiple diverse relations are associated with the same network. We conduct extensive experiments on social media data (one from a real-world blog site and the other from a popular content sharing site). Our model outperforms representative relational learning methods based on collective inference, especially when few labeled data are available. The sensitivity of this model and its connection to existing methods are also examined.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The classes of bloggers in BlogCatalog represent their personal interests.
“The classes of bloggers represent their personal interests.”
From A Comprehensive Survey on Graph Neural Networks (2021) · cites this paper as [127]
The BlogCatalog data set is a social network which consists of bloggers and their social relationships.
“The BlogCatalog data set is a social network which consists of bloggers and their social relationships.”
From A Comprehensive Survey on Graph Neural Networks (2021) · cites this paper as [127]
BlogCatalog is a network of social relationships provided by blogger authors.
“BlogCatalog [39] is a network of social relationships provided by blogger authors.”
From DeepWalk: online learning of social representations (2014) · cites this paper as [39]
DeepWalk outperforms other latent representation methods for creating social dimensions, especially when labeled nodes are scarce.
“DeepWalk outperforms other latent representation methods for creating social dimensions [39, 41], especially when labeled nodes are scarce.”
From DeepWalk: online learning of social representations (2014) · cites this paper as [39]
In Flickr, the labels represent the interest groups of the users.
“The labels represent the interest groups of the users such as ' black and white photos '.”
From DeepWalk: online learning of social representations (2014) · cites this paper as [39]
Flickr is a network of contacts between users of the photo sharing website.
“Flickr [39] is a network of the contacts between users of the photo sharing website.”
From DeepWalk: online learning of social representations (2014) · cites this paper as [39]
In BlogCatalog, the labels represent the topic categories provided by the authors.
“The labels represent the topic categories provided by the authors.”
From DeepWalk: online learning of social representations (2014) · cites this paper as [39]
Modularity generates a representation in R^d from the top-d eigenvectors of the Modularity matrix of G.
“Modularity [39]: This method generates a representation in R d from the topd eigenvectors of B , the Modularity matrix of G .”
From DeepWalk: online learning of social representations (2014) · cites this paper as [39]
Most methods require global information and are offline.
“Most methods require global information and are offline [16,39-41].”
From DeepWalk: online learning of social representations (2014) · cites this paper as [39]
The citation lists haven’t been fetched yet
References 44 · Cited by 799
- Authors
- Tang, L., & Liu, H.
- Affiliations
- Arizona State University (US)
- Venue
- Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
- Publisher
- ACM
- Published
- 2009-06-28
- Pages
- 817-826
- OpenAlex
- W2046253692
- Cited by
- 799
- References
- 44
- Citations by year
- 2026: 27 · 2025: 51 · 2024: 50 · 2023: 50 · 2022: 60 · 2021: 104 · 2020: 66 · 2019: 82 · 2018: 67 · 2017: 53 · 2016: 37 · 2015: 27 · 2014: 40 · 2013: 25 · 2012: 22
- FWCI
- 13.84
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion)
- Funders
- Air Force Office of Scientific Research
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Complex Network Analysis Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Keywords
- relational learning, social media, collective inference, discriminative learning, network characteristics, limited labeled data, blog data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
