Understanding data fusion within the framework of coupled matrix and tensor factorizations

Acar, Evrim; Rasmussen, Morten Arendt; Savorani, Francesco; Næs, Tormod; Bro, Rasmus

doi:10.1016/j.chemolab.2013.06.006

Cited by 87 publications

(87 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In these cases, relation schemas are known in advance, while we are interested in inducing such relation schemas from unstructured text. A PARAFAC (Harshman, 1970) based method for jointly factorizing a matrix and tensor for data fusion was proposed in (Acar et al, 2013). In such cases, the matrix is used to provide auxiliary information (Narita et al, 2012;Erdos and Miettinen, 2013).…”

Section: Related Workmentioning

confidence: 99%

Relation Schema Induction using Tensor Factorization with Side Information

Nimishakavi

Saini

Talukdar

2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Given a set of documents from a specific domain (e.g., medical research journals), how do we automatically build a Knowledge Graph (KG) for that domain? Automatic identification of relations and their schemas, i.e., type signature of arguments of relations (e.g., undergo(Patient, Surgery)), is an important first step towards this goal. We refer to this problem as Relation Schema Induction (RSI). In this paper, we propose Schema Induction using Coupled Tensor Factorization (SICTF), a novel tensor factorization method for relation schema induction. SICTF factorizes Open Information Extraction (OpenIE) triples extracted from a domain corpus along with additional side information in a principled way to induce relation schemas. To the best of our knowledge, this is the first application of tensor factorization for the RSI problem. Through extensive experiments on multiple real-world datasets, we find that SICTF is not only more accurate than state-of-the-art baselines, but also significantly faster (about 14x faster).

show abstract

Section: Related Workmentioning

confidence: 99%

Relation Schema Induction using Tensor Factorization with Side Information

Nimishakavi

Saini

Talukdar

2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…They propose a new algorithm that fuses a user's social network graph with a user-item rating matrix using factor analysis based on probabilistic matrix factorisation in order to find more accurate recommendations. Some recent work on data fusion (Acar et al, 2013) has sought to understand when data fusion is useful and when the analysis of in-dividual data sources may be more advantageous. Data fusion approaches have become popular for heterogeneous data as they handle the process of integration of multiple data and knowledge from the same real-world object into a consistent, accurate, and useful representation.…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, fusion approaches (Boström et al, 2007;Acar et al, 2013) are often used to deal with this mix of data as they can combine diverse data sources even when they differ in terms of representation. Generally speaking, fusion approaches focus on the analysis of multiple matrices and formulate data fusion as a collective factorisation of matrices.…”

Section: Related Workmentioning

confidence: 99%

An adaptive version of k-medoids to deal with the uncertainty in clustering heterogeneous data using an intermediary fusion approach

Mojahed

Iglesia

2016

Knowl Inf Syst

View full text Add to dashboard Cite

Abstract. This paper introduces Hk -medoids, a modified version of the standard kmedoids algorithm. The modification extends the algorithm for the problem of clustering complex heterogeneous objects that are described by a diversity of data types, e.g. text, images, structured data and time series. We first proposed an intermediary fusion approach to calculate fused similarities between objects, SMF, taking into account the similarities between the component elements of the objects using appropriate similarity measures. The fused approach entails uncertainty for incomplete objects or for objects which have diverging distances according to the different component. Our implementation of Hk -medoids proposed here works with the fused distances and deals with the uncertainty in the fusion process. We experimentally evaluate the potential of our proposed algorithm using five datasets with different combinations of data types that define the objects. Our results show the feasibility of the our algorithm and also they show a performance enhancement when comparing to the application of the original SMF approach in combination with a standard k -medoids that does not take uncertainty into account. In addition, from a theoretical point of view, our proposed algorithm has lower computation complexity than the popular PAM implementation.

show abstract

“…Hence, we insert a prior on the neural-hemodynamic coupling into the problem formulation, which admits to co-estimate the true underlying HRF from the data itself. We achieve this combined goal of extracting neural-hemodynamic sources and their temporal coupling by expressing the problem as a coupled matrix-tensor factorization (CMTF) [16], [17], where the fMRI data is a matrix of time samples × voxels and the EEG spectrogram is represented as a 3 rd order tensor of time samples × electrodes × frequencies as in [15]. The factorizations of both datasets are then constrained by a shared factor matrix in the temporal mode, which is transformed by a convolution with an unknown HRF in the fMRI factorization.…”

Section: Introductionmentioning

confidence: 99%

Flexible fusion of electroencephalography and functional magnetic resonance imaging: Revealing neural-hemodynamic coupling through structured matrix-tensor factorization

Eyndhoven

Hunyadi

Lathauwer

et al. 2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Abstract-Simultaneous recording of electroencephalographic (EEG) signals and functional magnetic resonance images (fMRI) has gained wide interest in brain research, thanks to the highly complementary spatiotemporal nature of both modalities. We propose a novel technique to extract sources of neural activity from the multimodal measurements, which relies on a structured form of coupled matrix-tensor factorization (CMTF). In a datasymmetric fashion, we characterize these underlying sources in the spatial, temporal and spectral domain, and estimate how the observations in EEG and fMRI are related through neurovascular coupling. That is, we explicitly account for the intrinsically variable nature of this coupling, allowing more accurate localization of the neural activity in time and space. We illustrate the effectiveness of this approach, which is shown to be robust to noise, by means of a simulation study. Hence, this provides a conceptually simple, yet effective alternative to other data-driven analysis methods in event-related or restingstate EEG-fMRI studies.

show abstract

Understanding data fusion within the framework of coupled matrix and tensor factorizations

Cited by 87 publications

References 22 publications

Relation Schema Induction using Tensor Factorization with Side Information

Relation Schema Induction using Tensor Factorization with Side Information

An adaptive version of k-medoids to deal with the uncertainty in clustering heterogeneous data using an intermediary fusion approach

Flexible fusion of electroencephalography and functional magnetic resonance imaging: Revealing neural-hemodynamic coupling through structured matrix-tensor factorization

Contact Info

Product

Resources

About