arXiv research

DEAL model predicts links for new nodes with only attribute info.

AOI algorithm improved predictive maintenance accuracy.

This article presents GuideR, a user-guided rule induction algorithm, which overcomes the largest limitation of the existing methods-the lack of the possibility to introduce user's preferences or domain knowledge to the rule learning process. Automatic selection of attributes and attribute ranges often leads to the sit…

The potential lack of fairness in the outputs of machine learning algorithms has recently gained attention both within the research community as well as in society more broadly. Surprisingly, there is no prior work developing tree-induction algorithms for building fair decision trees or fair random forests. These metho…

Endowing robots with human-like physical reasoning abilities remains challenging. We argue that existing methods often disregard spatio-temporal relations and by using Graph Neural Networks (GNNs) that incorporate a relational inductive bias, we can shift the learning process towards exploiting relations. In this work,…

If $p : Y \to X$ is an unramified covering map between two compact oriented surfaces of genus at least two, then it is proved that the embedding map, corresponding to $p$, from the Teichmüller space ${\cal T}(X)$, for $X$, to ${\cal T}(Y)$ actually extends to an embedding between the Thurston compactification of the tw…

New method for embedding large networks without attributes, achieving state-of-the-art performance.

Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in graph-structured data, several graph auto-encoders have recently been proposed, but they neglect to reco…

A novel algorithm for unsupervised graph representation learning combining coarsening and mutual information maximization.

CAWs learn temporal network dynamics without node identities or edge attributes.

New model generates unseen attribute combinations from limited data.

GLACE embeds large-scale attributed graphs effectively, preserving structure and attributes.

R2N learns interpretable rules and literals from numerical features.

In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models is not well understood. In this paper we propose a framework to systematically investigate bias and generalization in deep generative models …

Graphs (networks) are ubiquitous and allow us to model entities (nodes) and the dependencies (edges) between them. Learning a useful feature representation from graph data lies at the heart and success of many machine learning tasks such as classification, anomaly detection, link prediction, among many others. Many exi…

Methods that learn representations of nodes in a graph play a critical role in network analysis since they enable many downstream learning tasks. We propose Graph2Gauss - an approach that can efficiently learn versatile node embeddings on large scale (attributed) graphs that show strong performance on tasks such as lin…

Decision tree is an important method for both induction research and data mining, which is mainly used for model classification and prediction. ID3 algorithm is the most widely used algorithm in the decision tree so far. In this paper, the shortcoming of ID3's inclining to choose attributes with many values is discusse…

New proof shows exotic 4-manifolds exist without complex calculations.

New diagnostic tool for assessing approximate Bayesian inference.

We construct infinite sequences of pseudo-Anosov homeomorphisms without fixed points and leaving invariant a sequence of orientable measured foliations on the same topological surface and the same stratum of the space of abelian differentials. The existence of such sequences show that all pseudo-Anosov homeomorphisms f…

Let $Σ_{\infty, 1}$ be the inductive limit of compact oriented surfaces with one boundary component. We prove the center of the Goldman Lie algebra of the surface $Σ_{\infty,1}$ is spanned by the constant loop. A similar statement for a closed oriented surface was conjectured by Chas and Sullivan, and proved by Etingof…

Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions. However, most existing approaches require that all nodes in the graph are present during training of the embeddings; these previous approaches …

HyperBERT enhances BERT for node classification on text-attributed hypergraphs.

Data discretization is an important step in the process of machine learning, since it is easier for classifiers to deal with discrete attributes rather than continuous attributes. Over the years, several methods of performing discretization such as Boolean Reasoning, Equal Frequency Binning, Entropy have been proposed,…

Interval exchange maps are related to geodesic flows on translation surfaces; they correspond to the first return maps of the vertical flow on a transverse segment. The Rauzy-Veech induction on the space of interval exchange maps provides a powerful tool to analyze the Teichmueller geodesic flow on the moduli space of …

GTEA learns node representations in temporal interaction graphs.

COMET learns monotonic neural networks by incorporating counterexamples.

The study explores positive scalar curvature metrics on non-orientable manifolds and their covers.

Mobile gaming has emerged as a promising market with billion-dollar revenues. A variety of mobile game platforms and services have been developed around the world. One critical challenge for these platforms and services is to understand user churn behavior in mobile games. Accurate churn prediction will benefit many st…

This thesis explores supervised classification methods using Bayesian and exchangeability theories.

Emotional content is a crucial ingredient in user-generated videos. However, the sparsity of emotional expressions in the videos poses an obstacle to visual emotion analysis. In this paper, we propose a new neural approach, Bi-stream Emotion Attribution-Classification Network (BEAC-Net), to solve three related emotion …

Graph neural networks help AI agents learn more complex language.

In this work we propose a model that can manipulate individual visual attributes of objects in a real scene using examples of how respective attribute manipulations affect the output of a simulation. As an example, we train our model to manipulate the expression of a human face using nonphotorealistic 3D renders of a f…

Boost GNNs for node classification by incorporating label dependencies.

Random walks are at the heart of many existing network embedding methods. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to vertex identity. In this work, we introduce…

Graph Convolutional Networks (GCNs) are powerful models for learning representations of attributed graphs. To scale GCNs to large graphs, state-of-the-art methods use various layer sampling techniques to alleviate the "neighbor explosion" problem during minibatch training. We propose GraphSAINT, a graph sampling based …

Random walks are at the heart of many existing deep learning algorithms for graph data. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to node identity. In this work, …

Graph embedding techniques have been increasingly deployed in a multitude of different applications that involve learning on non-Euclidean data. However, existing graph embedding models either fail to incorporate node attribute information during training or suffer from node attribute noise, which compromises the accur…

In this work we present an adversarial training algorithm that exploits correlations in video to learn --without supervision-- an image generator model with a disentangled latent space. The proposed methodology requires only a few modifications to the standard algorithm of Generative Adversarial Networks (GAN) and invo…

BPI models 2D patterns on multiple planes and 3D scene from a single image.

A self-supervised debiasing method using rank regularization mitigates spurious correlations in neural networks.

Users in various web and mobile applications are vulnerable to attribute inference attacks, in which an attacker leverages a machine learning classifier to infer a target user's private attributes (e.g., location, sexual orientation, political view) from its public data (e.g., rating scores, page likes). Existing defen…

This paper applies machine learning techniques to student modeling. It presents a method for discovering high-level student behaviors from a very large set of low-level traces corresponding to problem-solving actions in a learning environment. Basic actions are encoded into sets of domain-dependent attribute-value patt…

A new method for name disambiguation in academic networks using multi-view attention and recurrent neural networks.

Proves left-orderability of mapping class groups of infinite-type surfaces.

Proposes a supervised VAE to reveal model invariances for interpretability.

Proves a conjecture about 3-manifold invariants using trees and asymptotic formulas.

New method relaxes spatial invariance in locally connected layers, improving accuracy.