
DifferentialCritic GAN: Generating What You Want by a Cue of Preferences
This paper proposes DifferentialCritic Generative Adversarial Network (...
read it

Online MultiAgent Forecasting with Interpretable Collaborative Graph Neural Network
This paper considers predicting future statuses of multiple agents in an...
read it

Out of Context: A New Clue for Context Modeling of Aspectbased Sentiment Analysis
Aspectbased sentiment analysis (ABSA) aims to predict the sentiment exp...
read it

Bayesian Active Learning by Disagreements: A Geometric Perspective
We present geometric Bayesian active learning by disagreements (GBALD), ...
read it

The Emerging Trends of MultiLabel Learning
Exabytes of data are generated daily by humans, leading to the growing n...
read it

A Survey of Labelnoise Representation Learning: Past, Present and Future
Classical machine learning implicitly assumes that labels of the trainin...
read it

Learning on AttributeMissing Graphs
Graphs with complete node attributes have been widely explored recently....
read it

Collaborative Generative Hashing for Marketing and Fast Coldstart Recommendation
Coldstart has being a critical issue in recommender systems with the ex...
read it

Deep Pairwise Hashing for Coldstart Recommendation
Recommendation efficiency and data sparsity problems have been regarded ...
read it

Graph Cross Networks with Vertex Infomax Pooling
We propose a novel graph cross network (GXN) to achieve comprehensive fe...
read it

Intrinsic Reward Driven Imitation Learning via Generative Model
Imitation learning in a highdimensional environment is challenging. Mos...
read it

Multiview Alignment and Generation in CCA via Consistent Latent Encoding
Multiview alignment, achieving onetoone correspondence of multiview ...
read it

Secure Metric Learning via Differential Pairwise Privacy
Distance Metric Learning (DML) has drawn much attention over the last tw...
read it

Face Hallucination with Finishing Touches
Obtaining a highquality frontal face image from a lowresolution (LR) n...
read it

Towards Sharper FirstOrder Adversary with Quantized Gradients
Despite the huge success of Deep Neural Networks (DNNs) in a wide spectr...
read it

Stochastic Implicit Natural Gradient for Blackbox Optimization
Blackbox optimization is primarily important for many computeintensive...
read it

Improving Generalization via Attribute Selection on Outofthebox Data
Zeroshot learning (ZSL) aims to recognize unseen objects (test classes)...
read it

Node Attribute Generation on Graphs
Graph structured data provide twofold information: graph structures and...
read it

Latent Adversarial Defence with Boundaryguided Generation
Deep Neural Networks (DNNs) have recently achieved great success in many...
read it

Fast and Robust Rank Aggregation against Model Misspecification
In rank aggregation, preferences from different users are summarized int...
read it

Curriculum Loss: Robust Learning and Generalization against Label Corruption
Generalization is vital important for many deep network models. It becom...
read it

Efficient Batch Blackbox Optimization with Deterministic Regret Bounds
In this work, we investigate blackbox optimization from the perspective...
read it

Marginalized Average Attentional Network for WeaklySupervised Learning
In weaklysupervised temporal action localization, previous works have f...
read it

Learning ImageSpecific Attributes by Hyperbolic Neighborhood Graph Propagation
As a kind of semantic representation of visual object descriptions, attr...
read it

Safeguarded Dynamic Label Regression for Generalized Noisy Supervision
Learning with noisy labels, which aims to reduce expensive labors on acc...
read it

How Does Disagreement Benefit Coteaching?
Learning with noisy labels is one of the most important question in weak...
read it

A Survey on Multioutput Learning
Multioutput learning aims to simultaneously predict multiple outputs gi...
read it

Privacypreserving Stochastic Gradual Learning
It is challenging for stochastic optimizations to handle largescale sen...
read it

TargetIndependent Active Learning via DistributionSplitting
To reduce the label complexity in Agnostic Active Learning (A^2 algorith...
read it

A Structured Perspective of Volumes on Active Learning
Active Learning (AL) is a learning task that requires learners interacti...
read it

Understanding VAEs in FisherShannon Plane
In information theory, Fisher information and Shannon information (entro...
read it

Geometric Active Learning via Enclosing Ball Boundary
Active Learning (AL) requires learners to retrain the classifier with th...
read it

Matrix Cocompletion for Multilabel Classification with Missing Features and Labels
We consider a challenging multilabel classification problem where both ...
read it

MultiContext Label Embedding
Label embedding plays an important role in zeroshot learning. Side info...
read it

Zeroshot Learning with Complementary Attributes
Zeroshot learning (ZSL) aims to recognize unseen objects using disjoint...
read it

VRSGD: A Simple Stochastic Variance Reduction Method for Machine Learning
In this paper, we propose a simple variant of the original SVRG, called ...
read it

Millionaire: A Hintguided Approach for Crowdsourcing
Modern machine learning is migrating to the era of complex models, which...
read it

Degeneration in VAE: in the Light of Fisher Information Loss
Variational Autoencoder (VAE) is one of the most popular generative mode...
read it

Online Product Quantization
Approximate nearest neighbor (ANN) search has achieved great success in ...
read it

Transfer Hashing with Privileged Information
Most existing learning to hash methods assume that there are sufficient ...
read it

A Novel Regularized Principal Graph Learning Framework on Explicit Graph Representation
Many scientific datasets are of high dimension, and the analysis usually...
read it

Matching Pursuit LASSO Part II: Applications and Sparse Recovery over Batch Signals
Matching Pursuit LASSIn Part I TanPMLPart1, a Matching Pursuit LASSO (MP...
read it

ParameterFree Spectral Kernel Learning
Due to the growing ubiquity of unlabeled data, learning with unlabeled d...
read it

Hierarchical Maximum Margin Learning for MultiClass Classification
Due to myriads of classes, designing accurate and efficient classifiers ...
read it

Efficient Optimization of Performance Measures by Classifier Adaptation
In practical applications, machine learning algorithms are often needed ...
read it
Ivor W. Tsang
is this you? claim profile