Related papers: Synthesize, Retrieve, and Propagate: A Unified Pre…
Tabular data is common yet typically incomplete, small in volume, and access-restricted due to privacy concerns. Synthetic data generation offers potential solutions. Many metrics exist for evaluating the quality of synthetic tabular data;…
Relationships among time series can be exploited as inductive biases in learning effective forecasting models. In hierarchical time series, relationships among subsets of sequences induce hard constraints (hierarchical inductive biases) on…
Urban forecasting has increasingly benefited from high-dimensional spatial data through two primary approaches: graph-based methods that rely on predefined spatial structures, and region-based methods that focus on learning expressive urban…
Capturing the composition patterns of relations is a vital task in knowledge graph completion. It also serves as a fundamental step towards multi-hop reasoning over learned knowledge. Previously, several rotation-based translational methods…
Semi-structured knowledge bases (SKBs) embed textual documents in a typed graph of entities and relations, and underpin applications such as product search, academic paper search, and precision-medicine inquiries. Existing hybrid retrieval…
With the growing interest on Network Analysis, Relational Data Mining is becoming an emphasized domain of Data Mining. This paper addresses the problem of extracting representative elements from a relational dataset. After defining the…
In this paper, we show that standard feed-forward and recurrent neural networks fail to learn abstract patterns based on identity rules. We propose Relation Based Pattern (RBP) extensions to neural network structures that solve this problem…
Most popular dimension reduction (DR) methods like t-SNE and UMAP are based on minimizing a cost between input and latent pairwise similarities. Though widely used, these approaches lack clear probabilistic foundations to enable a full…
Inference for probabilistic graphical models is still very much a practical challenge in large domains. The commonly used and effective belief propagation (BP) algorithm and its generalizations often do not converge when applied to hard,…
In the era of data-driven decision-making, accurate table-level representations and efficient table recommendation systems are becoming increasingly crucial for improving table management, discovery, and analysis. However, existing…
Tabular data prediction (TDP) is one of the most popular industrial applications, and various methods have been designed to improve the prediction performance. However, existing works mainly focus on feature interactions and ignore sample…
Many data we collect today are in tabular form, with rows as records and columns as attributes associated with each record. Understanding the structural relationship in tabular data can greatly facilitate the data science process.…
In many supervised learning tasks, the entities to be labeled are related to each other in complex ways and their labels are not independent. For example, in hypertext classification, the labels of linked pages are highly correlated. A…
In this paper, we propose a Spatial Robust Mixture Regression model to investigate the relationship between a response variable and a set of explanatory variables over the spatial domain, assuming that the relationships may exhibit complex…
Tabular synthesis models remain ineffective at capturing complex dependencies, and the quality of synthetic data is still insufficient for comprehensive downstream tasks, such as prediction under distribution shifts, automated…
Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities. However, effective aggregation of relevant…
We present GraPPa, an effective pre-training approach for table semantic parsing that learns a compositional inductive bias in the joint representations of textual and tabular data. We construct synthetic question-SQL pairs over…
The majority of data scientists and machine learning practitioners use relational data in their work [State of ML and Data Science 2017, Kaggle, Inc.]. But training machine learning models on data stored in relational databases requires…
The widespread deployment of wireless and mobile devices results in a proliferation of spatio-temporal data that is used in applications, e.g., traffic prediction, human mobility mining, and air quality prediction, where spatio-temporal…
The Paraphrase Database (PPDB; Ganitkevitch et al., 2013) is an extensive semantic resource, consisting of a list of phrase pairs with (heuristic) confidence estimates. However, it is still unclear how it can best be used, due to the…