Search Results for author:
Found 27 papers, 2 papers with code
Federated Causality Learning with Explainable Adaptive Optimization
We design a global optimization formula to naturally aggregate the causal graphs from client data and constrain the acyclicity of the global graph without exposing local data.
Long-tail Cross Modal Hashing
LtCMH firstly adopts auto-encoders to mine the individuality and commonality of different modalities by minimizing the dependency between the individuality of respective modalities and by enhancing the commonality of these modalities.
Hub-VAE: Unsupervised Hub-based Regularization of Variational Autoencoders
Exemplar-based methods rely on informative data points or prototypes to guide the optimization of learning algorithms.
Crowdsourcing with Meta-Workers: A New Way to Save the Budget
Due to the unreliability of Internet workers, it's difficult to complete a crowdsourcing project satisfactorily, especially when the tasks are multiple and the budget is limited.
Cross-modal Zero-shot Hashing by Label Attributes Embedding
Cross-modal hashing (CMH) is one of the most promising methods in cross-modal approximate nearest neighbor search.
Meta Cross-Modal Hashing on Long-Tailed Data
Due to the lack of training samples in the tail classes, MetaCMH first learns direct features from data in different modalities, and then introduces an associative memory module to learn the memory features of samples of the tail classes.
MetaMIML: Meta Multi-Instance Multi-Label Learning
Multi-Instance Multi-Label learning (MIML) models complex objects (bags), each of which is associated with a set of interrelated labels and composed with a set of instances.
Open-Set Crowdsourcing using Multiple-Source Transfer Learning
First, OSCrowd integrates crowd theme related datasets into a large source domain to facilitate partial transfer learning to approximate the label space inference of these tasks.
Group-Node Attention for Community Evolution Prediction
The task of predicting structural changes in communities over time is known as community evolution prediction.
Few-Shot Partial-Label Learning
Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class classifier by training on overly-annotated samples, each of which is annotated with a set of labels, but only one is the valid label.
Unsupervised Selective Manifold Regularized Matrix Factorization
Manifold regularization methods for matrix factorization rely on the cluster assumption, whereby the neighborhood structure of data in the input space is preserved in the factorization space.
Effects of Model Misspecification on Bayesian Bandits: Case Studies in UX Optimization
Bayesian bandits using Thompson Sampling have seen increasing success in recent years.
Multi-typed Objects Multi-view Multi-instance Multi-label Learning
Multi-typed objects Multi-view Multi-instance Multi-label Learning (M4L) deals with interconnected multi-typed objects (or bags) that are made of diverse instances, represented with heterogeneous feature views and annotated with a set of non-exclusive but semantically related labels.
Deep Incomplete Multi-View Multiple Clusterings
Multi-view clustering aims at exploiting information from multiple heterogeneous views to promote clustering.
Attention-Aware Answers of the Crowd
However, they all assume that workers' label quality is stable over time (always at the same level whenever they conduct the tasks).
Active Multi-Label Crowd Consensus
AMCC accounts for the commonality and individuality of workers, and assumes that workers can be organized into different groups.
Unsupervised Boosting-based Autoencoder Ensembles for Outlier Detection
Autoencoders, as a dimensionality reduction technique, have been recently applied to outlier detection.
Estimator Vectors: OOV Word Embeddings based on Subword and Context Clue Estimates
Semantic representations of words have been successfully extracted from unlabeled corpuses using neural network models like word2vec.
Cross-modal Zero-shot Hashing
It then defines an objective function to achieve deep feature learning compatible with the composite similarity preserving, category attribute space learning, and hashing coding function learning.
Weakly-paired Cross-Modal Hashing
FlexCMH first introduces a clustering-based matching strategy to explore the local structure of each cluster, and thus to find the potential correspondence between clusters (and samples therein) across modalities.
ActiveHNE: Active Heterogeneous Network Embedding
To maximize the profit of utilizing the rare and valuable supervised information in HNEs, we develop a novel Active Heterogeneous Network Embedding (ActiveHNE) framework, which includes two components: Discriminative Heterogeneous Network Embedding (DHNE) and Active Query in Heterogeneous Networks (AQHN).
Multi-View Multiple Clustering
It then uses matrix factorization on the individual matrices, along with the shared matrix, to generate diverse clusterings of high-quality.
Multi-View Multi-Instance Multi-Label Learning based on Collaborative Matrix Factorization
To preserve the intrinsic structure of the data matrices, M3Lcmf collaboratively factorizes them into low-rank matrices, explores the latent relationships between bags, instances, and labels, and selectively merges the data matrices.
Ranking-based Deep Cross-modal Hashing
Next, to expand the semantic representation power of hand-crafted features, RDCMH integrates the semantic ranking information into deep cross-modal hashing and jointly optimizes the compatible parameters of deep feature representations and of hashing functions.
Multiple Independent Subspace Clusterings
To ease this process, we consider diverse clusterings embedded in different subspaces, and analyze the embedding subspaces to shed light into the structure of each clustering.
Graph-based Selective Outlier Ensembles
A problem with this approach is that poor components are likely to negatively affect the quality of the consensus result.
Theoretical and Empirical Analysis of a Parallel Boosting Algorithm
In this paper we discuss a meta-learning algorithm (PSBML) which combines features of parallel algorithms with concepts from ensemble and boosting methodologies to achieve the desired scalability property.
