Optimizing Multi-Relational Factorization Models for Multiple Target Relations

Drumond, Lucas; Diaz-Aviles, Ernesto; Schmidt-Thieme, Lars; Nejdl, Wolfgang

doi:10.1145/2661829.2662052

Cited by 16 publications

(26 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each of the 12 features, we train a logistic regression classifier (we use logistic regression as a proof-of-concept), resulting in 12 classification models for predicting an individual as either depressed or non-depressed (anxious or non-anxious). We consider an additional predictive model -the most accurate HIN-based RS model from our previous work (Section 1) [28], DMF [13]. The above dynamic network-based classification models need to be superior to DMF for it to make sense to incorporate in the future the dynamic network data into the HIN-based framework, per the discussion in Section 1.…”

Section: Task 2: Do Individuals Who Have Different Evolving Network Pmentioning

confidence: 99%

The power of dynamic social networks to predict individuals’ mental health

et al. 2019

View full text Add to dashboard Cite

Precision medicine has received attention both in and outside the clinic. We focus on the latter, by exploiting the relationship between individuals' social interactions and their mental health to develop a predictive model of one's likelihood to be depressed or anxious from rich dynamic social network data. To our knowledge, we are the first to do this. Existing studies differ from our work in at least one aspect: they do not model social interaction data as a network; they do so but analyze static network data; they examine "correlation" between social networks and health but without developing a predictive model; or they study other individual traits but not mental health. In a systematic and comprehensive evaluation, we show that our predictive model that uses dynamic social network data is superior to its static network as well as non-network equivalents when run on the same data.

show abstract

Section: Task 2: Do Individuals Who Have Different Evolving Network Pmentioning

confidence: 99%

The power of dynamic social networks to predict individuals’ mental health

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In addition to these graph-oriented recommendation algorithms, we used the original DMF model restricted to only the direct network relations, to demonstrate the bene t of adding extended paths. Finally, we also used another multi-relational factorization model, CATSMF, using direct links of the network [6]. e CATSMF model [6] was introduced to improve the e ciency of the DMF model by limiting the parameters needed for the auxiliary relations by coupling them together.…”

Section: Comparison Algorithmsmentioning

confidence: 99%

“…Finally, we also used another multi-relational factorization model, CATSMF, using direct links of the network [6]. e CATSMF model [6] was introduced to improve the e ciency of the DMF model by limiting the parameters needed for the auxiliary relations by coupling them together.…”

Section: Comparison Algorithmsmentioning

confidence: 99%

Weighted Random Walk Sampling for Multi-Relational Recommendation

Vahedian

Burke

Mobasher

2017

Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization

View full text Add to dashboard Cite

In the information overloaded web, personalized recommender systems are essential tools to help users nd most relevant information. e most heavily-used recommendation frameworks assume user interactions that are characterized by a single relation. However, for many tasks, such as recommendation in social networks, user-item interactions must be modeled as a complex network of multiple relations, not only a single relation. Recently research on multi-relational factorization and hybrid recommender models has shown that using extended meta-paths to capture additional information about both users and items in the network can enhance the accuracy of recommendations in such networks. Most of this work is focused on unweighted heterogeneous networks, and to apply these techniques, weighted relations must be simpli ed into binary ones. However, information associated with weighted edges, such as user ratings, which may be crucial for recommendation, are lost in such binarization. In this paper, we explore a random walk sampling method in which the frequency of edge sampling is a function of edge weight, and apply this generate extended meta-paths in weighted heterogeneous networks. With this sampling technique, we demonstrate improved performance on multiple data sets both in terms of recommendation accuracy and model generation e ciency.

show abstract

“…This method has shown state-of-the-art performances on relational datasets [26], although the number of relation types is usually modest (less than 100). Extensions have recently been proposed in [9], [15] to handle multirelational data with a large number of relation types.…”

Section: Multi-relational Learningmentioning

confidence: 99%

“…The latter treat multi-relational information (i.e., multigraph) as constraints to the learning process, whereas ours casts multirelational information into multi-relational features that in turn serve as additional information to be augmented into the learning process. Finally, CSL is more generic/flexible than the matrix/tensor factorization methods [7], [9], [13], [15], [26], [29]. These methods rely on low-rank assumption for matrix/tensor decomposition, and do not yet cater for explicit (i.e., non-latent) features defined for each entity.…”

Section: Our Approachmentioning

confidence: 99%

Collective Semi-Supervised Learning for User Profiling in Social Media

Oentaryo,

Lim,

Chua

et al. 2016

Preprint

View full text Add to dashboard Cite

The abundance of user-generated data in social media has incentivized the development of methods to infer the latent attributes of users, which are crucially useful for personalization, advertising and recommendation. However, the current user profiling approaches have limited success, due to the lack of a principled way to integrate different types of social relationships of a user, and the reliance on scarcely-available labeled data in building a prediction model. In this paper, we present a novel solution termed Collective Semi-Supervised Learning (CSL), which provides a principled means to integrate different types of social relationship and unlabeled data under a unified computational framework. The joint learning from multiple relationships and unlabeled data yields a computationally sound and accurate approach to model user attributes in social media. Extensive experiments using Twitter data have demonstrated the efficacy of our CSL approach in inferring user attributes such as account type and marital status. We also show how CSL can be used to determine important user features, and to make inference on a larger user population.

show abstract

Optimizing Multi-Relational Factorization Models for Multiple Target Relations

Cited by 16 publications

References 17 publications

The power of dynamic social networks to predict individuals’ mental health

The power of dynamic social networks to predict individuals’ mental health

Weighted Random Walk Sampling for Multi-Relational Recommendation

Collective Semi-Supervised Learning for User Profiling in Social Media

Contact Info

Product

Resources

About