Interpreting multi-variate models with setPCA
- URL: http://arxiv.org/abs/2111.09138v1
- Date: Wed, 17 Nov 2021 14:22:19 GMT
- Title: Interpreting multi-variate models with setPCA
- Authors: Nordine Aouni, Luc Linders, David Robinson, Len Vandelaer, Jessica
Wiezorek, Geetesh Gupta, Rachel Cavill
- Abstract summary: We present an algorithmic method which has been developed to integrate "omics" data with existing databases of background knowledge.
We have produced a Graphical User Interface (GUI) in Matlab which allows the overlay of known set information onto the loadings plot.
For each known set the optimal convex hull, covering a subset of elements from the known set, is found through a search algorithm and displayed.
- Score: 0.038478302549231076
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Principal Component Analysis (PCA) and other multi-variate models are often
used in the analysis of "omics" data. These models contain much information
which is currently neither easily accessible nor interpretable. Here we present
an algorithmic method which has been developed to integrate this information
with existing databases of background knowledge, stored in the form of known
sets (for instance genesets or pathways). To make this accessible we have
produced a Graphical User Interface (GUI) in Matlab which allows the overlay of
known set information onto the loadings plot and thus improves the
interpretability of the multi-variate model. For each known set the optimal
convex hull, covering a subset of elements from the known set, is found through
a search algorithm and displayed. In this paper we discuss two main topics; the
details of the search algorithm for the optimal convex hull for this problem
and the GUI interface which is freely available for download for academic use.
Related papers
- Learning Representations without Compositional Assumptions [79.12273403390311]
We propose a data-driven approach that learns feature set dependencies by representing feature sets as graph nodes and their relationships as learnable edges.
We also introduce LEGATO, a novel hierarchical graph autoencoder that learns a smaller, latent graph to aggregate information from multiple views dynamically.
arXiv Detail & Related papers (2023-05-31T10:36:10Z) - Scalable Batch Acquisition for Deep Bayesian Active Learning [70.68403899432198]
In deep active learning, it is important to choose multiple examples to markup at each step.
Existing solutions to this problem, such as BatchBALD, have significant limitations in selecting a large number of examples.
We present the Large BatchBALD algorithm, which aims to achieve comparable quality while being more computationally efficient.
arXiv Detail & Related papers (2023-01-13T11:45:17Z) - Interpretable ML for Imbalanced Data [22.355966235617014]
Imbalanced data compounds the black-box nature of deep networks because the relationships between classes may be skewed and unclear.
Existing methods that investigate imbalanced data complexity are geared toward binary classification, shallow learning models and low dimensional data.
We propose a set of techniques that can be used by both deep learning model users to identify, visualize and understand class prototypes, sub-concepts and outlier instances.
arXiv Detail & Related papers (2022-12-15T11:50:31Z) - Learning Implicit Feature Alignment Function for Semantic Segmentation [51.36809814890326]
Implicit Feature Alignment function (IFA) is inspired by the rapidly expanding topic of implicit neural representations.
We show that IFA implicitly aligns the feature maps at different levels and is capable of producing segmentation maps in arbitrary resolutions.
Our method can be combined with improvement on various architectures, and it achieves state-of-the-art accuracy trade-off on common benchmarks.
arXiv Detail & Related papers (2022-06-17T09:40:14Z) - Benchpress: A Scalable and Versatile Workflow for Benchmarking Structure
Learning Algorithms [1.7188280334580197]
Probabilistic graphical models are one common approach to modelling the data generating mechanism.
We present a novel Snakemake workflow called Benchpress for producing scalable, reproducible, and platform-independent benchmarks.
We demonstrate the applicability of this workflow for learning Bayesian networks in five typical data scenarios.
arXiv Detail & Related papers (2021-07-08T14:19:28Z) - Learning Feature Aggregation for Deep 3D Morphable Models [57.1266963015401]
We propose an attention based module to learn mapping matrices for better feature aggregation across hierarchical levels.
Our experiments show that through the end-to-end training of the mapping matrices, we achieve state-of-the-art results on a variety of 3D shape datasets.
arXiv Detail & Related papers (2021-05-05T16:41:00Z) - Captum: A unified and generic model interpretability library for PyTorch [49.72749684393332]
We introduce a novel, unified, open-source model interpretability library for PyTorch.
The library contains generic implementations of a number of gradient and perturbation-based attribution algorithms.
It can be used for both classification and non-classification models.
arXiv Detail & Related papers (2020-09-16T18:57:57Z) - Information Theoretic Meta Learning with Gaussian Processes [74.54485310507336]
We formulate meta learning using information theoretic concepts; namely, mutual information and the information bottleneck.
By making use of variational approximations to the mutual information, we derive a general and tractable framework for meta learning.
arXiv Detail & Related papers (2020-09-07T16:47:30Z) - NASE: Learning Knowledge Graph Embedding for Link Prediction via Neural
Architecture Search [9.634626241415916]
Link prediction is the task of predicting missing connections between entities in the knowledge graph (KG)
Previous work has tried to use Automated Machine Learning (AutoML) to search for the best model for a given dataset.
We propose a novel Neural Architecture Search (NAS) framework for the link prediction task.
arXiv Detail & Related papers (2020-08-18T03:34:09Z) - StackGenVis: Alignment of Data, Algorithms, and Models for Stacking Ensemble Learning Using Performance Metrics [4.237343083490243]
In machine learning (ML), ensemble methods such as bagging, boosting, and stacking are widely-established approaches.
StackGenVis is a visual analytics system for stacked generalization.
arXiv Detail & Related papers (2020-05-04T15:43:55Z) - Analyzing Knowledge Graph Embedding Methods from a Multi-Embedding
Interaction Perspective [3.718476964451589]
Real-world knowledge graphs are usually incomplete, so knowledge graph embedding methods have been proposed to address this issue.
These methods represent entities and relations as embedding vectors in semantic space and predict the links between them.
We propose a new multi-embedding model based on quaternion algebra and show that it achieves promising results using popular benchmarks.
arXiv Detail & Related papers (2019-03-27T13:09:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.