A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Method learns relational features for Gaifman models from knowledge bases.
We propose Macau, a powerful and flexible Bayesian factorization method for heterogeneous data. Our model can factorize any set of entities and relations that can be represented by a relational model, including tensors and also multiple relations for each entity. Macau can also incorporate side information, specificall…
Graph Neural Networks improve machine learning on relational databases.
Feature extraction becomes increasingly important as data grows high dimensional. Autoencoder as a neural network based feature extraction method achieves great success in generating abstract features of high dimensional data. However, it fails to consider the relationships of data samples which may affect experimental…
SAG-VAE learns data representations and feature relations end-to-end.
A general formulation of optimization problems in which various candidate solutions may use different feature-sets is presented, encompassing supervised classification, automated program learning and other cases. A novel characterization of the concept of a "good quality feature" for such an optimization problem is pro…
LazyBum uses lazy propositionalization to learn from relational data.
Time-related features improve time series forecasting models.
Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another …
This paper considers the multi-task learning problem and in the setting where some relevant features could be shared across few related tasks. Most of the existing methods assume the extent to which the given tasks are related or share a common feature space to be known apriori. In real-world applications however, it i…
Attention-based embeddings improve relation prediction in incomplete KGs.
Latent features learned by deep learning approaches have proven to be a powerful tool for machine learning. They serve as a data abstraction that makes learning easier by capturing regularities in data explicitly. Their benefits motivated their adaptation to relational learning context. In our previous work, we introdu…
Model predicts severity of traffic accidents using spatial and temporal features.
We study the following problem: given an Einstein metric on a manifold, characterize and study all Einstein metrics which are pointwise projective to the given one. By definition, two metrics are said to be pointwise projectively related if they have the same geodesics as point sets. This is closely related to Hilbert'…
The paper uses AI to analyze ECG data, revealing age-related changes and identifying key features.
Phone sensors could be useful in assessing changes in gait that occur with alcohol consumption. This study determined (1) feasibility of collecting gait-related data during drinking occasions in the natural environment, and (2) how gait-related features measured by phone sensors relate to estimated blood alcohol concen…
Relational data representations have become an increasingly important topic due to the recent proliferation of network datasets (e.g., social, biological, information networks) and a corresponding increase in the application of statistical relational learning (SRL) algorithms to these domains. In this article, we exami…
The goal of unsupervised representation learning is to extract a new representation of data, such that solving many different tasks becomes easier. Existing methods typically focus on vectorized data and offer little support for relational data, which additionally describe relationships among instances. In this work we…
Graphs from features improve classification accuracy in tasks.
A new method uses Shapley values to select important features for classification.
There are time series that are amenable to recurrent neural network (RNN) solutions when treated as sequences, but some series, e.g. asynchronous time series, provide a richer variation of feature types than current RNN cells take into account. In order to address such situations, we introduce a unified RNN that handle…
End-to-end model detects articulatory features from speech data.
New private learning algorithms improve utility in tasks with public features.
We present a new approach for detecting related crime series, by unsupervised learning of the latent feature embeddings from narratives of crime record via the Gaussian-Bernoulli Restricted Boltzmann Machines (RBM). This is a drastically different approach from prior work on crime analysis, which typically considers on…
We consider analysis of relational data (a matrix), in which the rows correspond to subjects (e.g., people) and the columns correspond to attributes. The elements of the matrix may be a mix of real and categorical. Each subject and attribute is characterized by a latent binary feature vector, and an inferred matrix map…
Novel unsupervised feature selection method using multi-step Markov transition probability.
Proposes a new method for predicting missing relations in knowledge graphs.
We explore the generalization of scattering transforms from traditional (e.g., image or audio) signals to graph data, analogous to the generalization of ConvNets in geometric deep learning, and the utility of extracted graph features in graph data analysis. In particular, we focus on the capacity of these features to r…
Rk-means clusters relational data without full matrix, speeding up clustering.
TGG improves zero-shot and few-shot learning by explicitly modeling and utilizing seen-unseen domain relations.
A new GNN module learns geometric scattering features for better graph classification and feature exploration.
Improves unsupervised feature learning with an exclusivity concept.
Researchers formalize PD and PFI to relate them to data generating process.
FIBS extracts relevant features from IBTSs for classification.
Proposes a graph-based text representation for improved sentiment analysis.
Identifies features most relevant to concept drift in data.
MinShap improves feature selection accuracy and stability in complex models.
Paper proposes a CNN for speech emotion recognition using center loss and reconstruction.
The study uses music chords to predict Brazilian music genres.
We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adap…
MCNet improves uncertainty calibration in online advertising by modeling complex relations and balancing performance.
We consider the two problems of predicting links in a dynamic graph sequence and predicting functions defined at each node of the graph. In many applications, the solution of one problem is useful for solving the other. Indeed, if these functions reflect node features, then they are related through the graph structure.…
"Deep Learning" methods attempt to learn generic features in an unsupervised fashion from a large unlabelled data set. These generic features should perform as well as the best hand crafted features for any learning problem that makes use of this data. We provide a definition of generic features, characterize when it i…
In this article, we extend the conventional framework of convolutional-Restricted-Boltzmann-Machine to learn highly abstract features among abitrary number of time related input maps by constructing a layer of multiplicative units, which capture the relations among inputs. In many cases, more than two maps are strongly…
In this paper, we aim to develop a unified view of causal and non-causal feature selection methods. The unified view will fill in the gap in the research of the relation between the two types of methods. Based on the Bayesian network framework and information theory, we first show that causal and non-causal feature sel…
Paper proposes a neural network to improve traffic flow forecasting.
New network learns image features inductively for disease classification.
This study approximates neural network features for modeling relations and attention mechanisms.