Search Results for author:
Found 64 papers, 13 papers with code
When an Active Learner Meets a Black-box Teacher
In this paper, we introduce a machine teacher who provides a black-box teaching hypothesis for an active learner, where the teaching hypothesis is an effective approximation for the optimal hypothesis.
Data-Efficient Learning via Minimizing Hyperspherical Energy
Finally, we demonstrate the empirical performance of MHEAL in a wide range of applications on data-efficient learning, including deep clustering, distribution matching, version space sampling and deep active learning.
Latent Boundary-guided Adversarial Training
Adversarial training is proved to be the most effective strategy that injects adversarial examples into model training to improve the robustness of DNN models to adversarial attacks.
Neural Subgraph Explorer: Reducing Noisy Information via Target-Oriented Syntax Graph Pruning
In this paper, we propose a novel model termed Neural Subgraph Explorer, which (1) reduces the noisy information via pruning target-irrelevant nodes on the syntax graph; (2) introduces beneficial first-order connections between the target and its related words into the obtained graph.
Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations
Motivated by the idea of meta-augmentation, in this paper, by treating a user's preference over items as a task, we propose a so-called Diverse Preference Augmentation framework with multiple source domains based on meta-learning (referred to as MetaDPA) to i) generate diverse ratings in a new domain of interest (known as target domain) to handle overfitting on the case of sparse interactions, and to ii) learn a preference model in the target domain via a meta-learning scheme to alleviate cold-start issues.
DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act Recognition
To implement our framework, we propose a novel model dubbed DARER, which first generates the context-, speaker- and temporal-sensitive utterance representations via modeling SATG, then conducts recurrent dual-task relational reasoning on DRTG, in which process the estimated label distributions act as key clues in prediction-level interactions.
Taming Overconfident Prediction on Unlabeled Data from Hindsight
The prediction uncertainty is typically expressed as the \emph{entropy} computed by the transformed probabilities in output space.
TRIP: Refining Image-to-Image Translation via Rival Preferences
In particular, we simultaneously train two modules: a generator that translates an input image to the desired image with smooth subtle changes with respect to the interested attributes; and a ranker that ranks rival preferences consisting of the input image and the desired image.
Edge but not Least: Cross-View Graph Pooling
Graph neural networks have emerged as a powerful model for graph representation learning to undertake graph-level prediction tasks.
A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecasting
Therefore, there are two fundamental views which can be used to analyze MTS data, namely the spatial view and the temporal view.
Understand me, if you refer to Aspect Knowledge: Knowledge-aware Gated Recurrent Memory Network
Aspect-level sentiment classification (ASC) aims to predict the fine-grained sentiment polarity towards a given aspect mentioned in a review.
Differential-Critic GAN: Generating What You Want by a Cue of Preferences
This paper proposes Differential-Critic Generative Adversarial Network (DiCGAN) to learn the distribution of user-desired data when only partial instead of the entire dataset possesses the desired property, which generates desired data that meets user's expectations and can assist in designing biological products with desired properties.
Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Network
This paper considers predicting future statuses of multiple agents in an online fashion by exploiting dynamic interactions in the system.
Out of Context: A New Clue for Context Modeling of Aspect-based Sentiment Analysis
In these aspect-aware context encoders, the semantics of the given aspect is used to regulate the information flow.
Distribution Matching for Machine Teaching
This optimization solver is in general ineffective when the student learner does not disclose any cue of the learning parameters.
Bayesian Active Learning by Disagreements: A Geometric Perspective
We present geometric Bayesian active learning by disagreements (GBALD), a framework that performs BALD on its core-set construction interacting with model uncertainty estimation.
The Emerging Trends of Multi-Label Learning
Exabytes of data are generated daily by humans, leading to the growing need for new efforts in dealing with the grand challenges for multi-label learning brought by big data.
A Survey of Label-noise Representation Learning: Past, Present and Future
Classical machine learning implicitly assumes that labels of the training data are sampled from a clean distribution, which can be too restrictive for real-world scenarios.
Deep Pairwise Hashing for Cold-start Recommendation
Specifically, we first pre-train robust item representation from item content data by a Denoising Auto-encoder instead of other deterministic deep learning frameworks; then we finetune the entire framework by adding a pairwise loss objective with discrete constraints; moreover, DPH aims to minimize a pairwise ranking loss that is consistent with the ultimate goal of recommendation.
Collaborative Generative Hashing for Marketing and Fast Cold-start Recommendation
Cold-start has being a critical issue in recommender systems with the explosion of data in e-commerce.
Subgroup-based Rank-1 Lattice Quasi-Monte Carlo
We theoretically prove a lower and an upper bound of the minimum pairwise distance of any non-degenerate rank-1 lattice.
Graph Cross Networks with Vertex Infomax Pooling
Based on trainable hierarchical representations of a graph, GXN enables the interchange of intermediate features across scales to promote information flow.
Deep N-ary Error Correcting Output Codes
To facilitate the training of N-ary ECOC with deep learning base learners, we further propose three different variants of parameter sharing architectures for deep N-ary ECOC.
Intrinsic Reward Driven Imitation Learning via Generative Model
Thus, our module provides the imitation agent both the intrinsic intention of the demonstrator and a better exploration ability, which is critical for the agent to outperform the demonstrator.
Multi-view Alignment and Generation in CCA via Consistent Latent Encoding
Multi-view alignment, achieving one-to-one correspondence of multi-view inputs, is critical in many real-world multi-view applications, especially for cross-view data analysis problems.
Secure Metric Learning via Differential Pairwise Privacy
This paper studies, for the first time, how pairwise information can be leaked to attackers during distance metric learning, and develops differential pairwise privacy (DPP), generalizing the definition of standard differential privacy, for secure metric learning.
Face Hallucination with Finishing Touches
The coarse-level FHnet generates a frontal coarse HR face and then the fine-level FHnet makes use of the facial component appearance prior, i. e., fine-grained facial components, to attain a frontal HR face image with authentic details.
Towards Sharper First-Order Adversary with Quantized Gradients
However, in state-of-the-art first-order attacks, adversarial examples with sign gradients retain the sign information of each gradient component but discard the relative magnitude between components.
Collaborative Generated Hashing for Market Analysis and Fast Cold-start Recommendation
Cold-start and efficiency issues of the Top-k recommendation are critical to large-scale recommender systems.
Black-box Optimizer with Implicit Natural Gradient
Empirically, our method with full matrix update achieves competitive performance compared with one of the state-of-the-art method CMA-ES on benchmark test problems.
Improving Generalization via Attribute Selection on Out-of-the-box Data
Unfortunately, previous attribute selection methods are conducted based on the seen data, and their selected attributes have poor generalization capability to the unseen data, which is unavailable in the training stage of ZSL tasks.
Node Attribute Generation on Graphs
NANG learns a unifying latent representation which is shared by both node attributes and graph structures and can be translated to different modalities.
Latent Adversarial Defence with Boundary-guided Generation
The proposed LAD method improves the robustness of a DNN model through adversarial training on generated adversarial examples.
Fast and Robust Rank Aggregation against Model Misspecification
In rank aggregation, preferences from different users are summarized into a total order under the homogeneous data assumption.
Curriculum Loss: Robust Learning and Generalization against Label Corruption
Although the 0-1 loss has some robust properties, it is difficult to optimize.
Efficient Batch Black-box Optimization with Deterministic Regret Bounds
In this work, we investigate black-box optimization from the perspective of frequentist kernel methods.
Marginalized Average Attentional Network for Weakly-Supervised Learning
The MAAN employs a novel marginalized average aggregation (MAA) module and learns a set of latent discriminative probabilities in an end-to-end fashion.
Ranked #7 on
Weakly Supervised Action Localization
on ActivityNet-1.3
(mAP@0.5 metric)
Weakly Supervised Action Localization
Weakly-supervised Temporal Action Localization
+1
Learning Image-Specific Attributes by Hyperbolic Neighborhood Graph Propagation
In most of existing attribute-based research, class-specific attributes (CSA), which are class-level annotations, are usually adopted due to its low annotation cost for each class instead of each individual image.
Mental Fatigue Monitoring using Brain Dynamics Preferences
Furthermore, a transition matrix is introduced to characterize the reliability of each channel used in EEG data, which helps in learning brain dynamics preferences only from informative EEG channels.
Safeguarded Dynamic Label Regression for Generalized Noisy Supervision
We further generalize LCCN for open-set noisy labels and the semi-supervised setting.
Ranked #25 on
Image Classification
on Clothing1M
(using extra training data)
How does Disagreement Help Generalization against Label Corruption?
Learning with noisy labels is one of the hottest problems in weakly-supervised learning.
Ranked #9 on
Learning with noisy labels
on CIFAR-10N-Worst
A Survey on Multi-output Learning
Multi-output learning aims to simultaneously predict multiple outputs given an input.
Privacy-preserving Stochastic Gradual Learning
PRESTIGE bridges private updates of the primal variable (by private sampling) with the gradual curriculum learning (CL).
Target-Independent Active Learning via Distribution-Splitting
By discovering the connections between hypothesis and input distribution, we map the volume of version space into the number density and propose a target-independent distribution-splitting strategy with the following advantages: 1) provide theoretical guarantees on reducing label complexity and error rate as volume-splitting; 2) break the curse of initial hypothesis; 3) provide model guidance for a target-independent AL algorithm in real AL tasks.
XAI Beyond Classification: Interpretable Neural Clustering
The second is implementing discrete $k$-means with a differentiable neural network that embraces the advantages of parallel computing, online clustering, and clustering-favorable representation learning.
A Structured Perspective of Volumes on Active Learning
In this paper, we approximate the version space to a structured {hypersphere} that covers most of the hypotheses, and then divide the available AL sampling approaches into two kinds of strategies: Outer Volume Sampling and Inner Volume Sampling.
Understanding VAEs in Fisher-Shannon Plane
In information theory, Fisher information and Shannon information (entropy) are respectively used to quantify the uncertainty associated with the distribution modeling and the uncertainty in specifying the outcome of given variables.
Matrix Co-completion for Multi-label Classification with Missing Features and Labels
We consider a challenging multi-label classification problem where both feature matrix $\X$ and label matrix $\Y$ have missing entries.
Label Embedding with Partial Heterogeneous Contexts
In this paper, we propose a general Partial Heterogeneous Context Label Embedding (PHCLE) framework to address these challenges.
Complementary Attributes: A New Clue to Zero-Shot Learning
Extensive experiments on five ZSL benchmark datasets and the large-scale ImageNet dataset demonstrate that the proposed complementary attributes and rank aggregation can significantly and robustly improve existing ZSL methods and achieve the state-of-the-art performance.
VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning
In this paper, we propose a simple variant of the original SVRG, called variance reduced stochastic gradient descent (VR-SGD).
Degeneration in VAE: in the Light of Fisher Information Loss
While enormous progress has been made to Variational Autoencoder (VAE) in recent years, similar to other deep networks, VAE with deep networks suffers from the problem of degeneration, which seriously weakens the correlation between the input and the corresponding latent codes, deviating from the goal of the representation learning.
Online Product Quantization
The experiments demonstrate that our online PQ model is both time-efficient and effective for ANN search in dynamic large scale databases compared with baseline methods and the idea of partial PQ codebook update further reduces the update cost.
Transfer Hashing with Privileged Information
Specifically, we extend the standard learning to hash method, Iterative Quantization (ITQ), in a transfer learning manner, namely ITQ+.
On the Convergence of A Family of Robust Losses for Stochastic Gradient Descent
The convergence of Stochastic Gradient Descent (SGD) using convex loss functions has been widely studied.
N-ary Error Correcting Coding Scheme
The coding matrix design plays a fundamental role in the prediction performance of the error correcting output codes (ECOC)-based multi-class task.
A Novel Regularized Principal Graph Learning Framework on Explicit Graph Representation
As showcases, models that can learn a spanning tree or a weighted undirected $\ell_1$ graph are proposed, and a new learning algorithm is developed that learns a set of principal points and a graph structure from data, simultaneously.
Event Detection using Multi-Level Relevance Labels and Multiple Features
We address the challenging problem of utilizing related exemplars for complex event detection while multiple features are available.
Convex and Scalable Weakly Labeled SVMs
In this paper, we study the problem of learning from weakly labeled data, where labels of the training examples are incomplete.
Matching Pursuit LASSO Part II: Applications and Sparse Recovery over Batch Signals
Matching Pursuit LASSIn Part I \cite{TanPMLPart1}, a Matching Pursuit LASSO ({MPL}) algorithm has been presented for solving large-scale sparse recovery (SR) problems.
Towards Ultrahigh Dimensional Feature Selection for Big Data
In this paper, we present a new adaptive feature scaling scheme for ultrahigh-dimensional feature selection on Big Data.
A Feature Selection Method for Multivariate Performance Measures
The analyses by comparing with the state-of-the-art feature selection methods show that the proposed method is superior to others.
Efficient Multi-Template Learning for Structured Prediction
To alleviate this issue, in this paper, we propose a novel multiple template learning paradigm to learn structured prediction and the importance of each template simultaneously, so that hundreds of arbitrary templates could be added into the learning model without caution.
