Search Results for author:
Found 41 papers, 14 papers with code
Learning VAE-LDA Models with Rounded Reparameterization Trick
The introduction of VAE provides an efficient framework for the learning of generative models, including generative topic models.
A Transformational Biencoder with In-Domain Negative Sampling for Zero-Shot Entity Linking
As like previous work, we rely on negative entities to encourage our model to discriminate the golden entities during training.
On f-Divergence Principled Domain Adaptation: An Improved Framework
Unsupervised domain adaptation (UDA) plays a crucial role in addressing distribution shifts in machine learning.
On robust overfitting: adversarial training induced distribution matters
Adversarial training may be regarded as standard training with a modified loss function.
Anaphor Assisted Document-Level Relation Extraction
Existing methods focus on building a heterogeneous document graph to model the internal structure of an entity and the external interaction between entities.
Narrowing the Gap between Supervised and Unsupervised Sentence Representation Learning with Large Language Model
An intriguing phenomenon in CSE is the significant performance gap between supervised and unsupervised methods, with their only difference lying in the training data.
Adversarial Defenses via Vector Quantization
Building upon Randomized Discretization, we develop two novel adversarial defenses against white-box PGD attacks, utilizing vector quantization in higher dimensional spaces.
ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification
Few-shot text classification has recently been promoted by the meta-learning paradigm which aims to identify target classes with knowledge transferred from source classes with sets of small tasks named episodes.
Adversarial Word Dilution as Text Data Augmentation in Low-Resource Regime
Data augmentation is widely used in text classification, especially in the low-resource regime where a few examples for each class are available during training.
Over-training with Mixup May Hurt Generalization
Mixup, which creates synthetic training instances by linearly interpolating random sample pairs, is a simple and yet effective regularization technique to boost the performance of deep models trained with SGD.
Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction
Inspired by the theoretical foundations in domain adaptation [2], we propose a new SSL approach that opts for selecting target samples whose model output from a domain-specific teacher and student network disagree on the unlabelled target data, in an effort to boost the target domain performance.
Tighter Information-Theoretic Generalization Bounds from Supersamples
In this work, we present a variety of novel information-theoretic generalization bounds for learning algorithms, from the supersample setting of Steinke & Zakynthinou (2020)-the setting of the "conditional mutual information" framework.
Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States
Using this estimate, we apply the PAC-Bayes-like information-theoretic bounds developed in both Xu & Raginsky (2017) and Negrea et al. (2019) to obtain generalization upper bounds in terms of the KL divergence between the steady-state weight distribution of SGD with respect to a prior distribution.
Information-Theoretic Analysis of Unsupervised Domain Adaptation
This paper uses information-theoretic tools to analyze the generalization error in unsupervised domain adaptation (UDA).
Cross Domain Few-Shot Learning via Meta Adversarial Training
Few-shot relation classification (RC) is one of the critical problems in machine learning.
cross-domain few-shot learning
Few-Shot Relation Classification
Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation
Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings.
Ranked #1 on
Subjectivity Analysis
on SUBJ
ifMixup: Interpolating Graph Pair to Regularize Graph Classification
We present a simple and yet effective interpolation-based regularization technique, aiming to improve the generalization of Graph Neural Networks (GNNs) on supervised graph classification.
On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications
This paper follows up on a recent work of Neu et al. (2021) and presents some new information-theoretic upper bounds for the generalization error of machine learning models, such as neural networks, trained with SGD.
Intrusion-Free Graph Mixup
We present a simple and yet effective interpolation-based regularization technique to improve the generalization of Graph Neural Networks (GNNs).
Robust Regularization with Adversarial Labelling of Perturbed Samples
The ALPS regularization objective is formulated as a min-max problem, in which the outer problem is minimizing an upper-bound of the VRM loss, and the inner problem is L$_1$-ball constrained adversarial labelling on perturbed sample.
Attention as Inference via Fenchel Duality
In particular, we describe a convex optimization problem that arises in a family of estimation tasks commonly appearing in the design of deep learning models.
On the Generalization of Neural Networks Trained with SGD: Information-Theoretical Bounds and Implications
Understanding the generalization behaviour of deep neural networks is an important theme of modern research in machine learning.
On the Dynamics of Training Attention Models
The attention mechanism has been widely used in deep neural networks as a model component.
Regularizing Neural Networks via Adversarial Model Perturbation
This work proposes a new regularization scheme, based on the understanding that the flat local minima of the empirical risk cause the model to generalize better.
Ranked #8 on
Image Classification
on SVHN
Parallel Interactive Networks for Multi-Domain Dialogue State Generation
In this study, we argue that the incorporation of these dependencies is crucial for the design of MDST and propose Parallel Interactive Networks (PIN) to model these dependencies.
Dialogue State Tracking
Multi-domain Dialogue State Tracking
Neural Dialogue State Tracking with Temporally Expressive Networks
Existing DST models either ignore temporal feature dependencies across dialogue turns or fail to explicitly model temporal state dependencies in a dialogue.
On SkipGram Word Embedding Models with Negative Sampling: Unified Framework and Impact of Noise Distributions
SkipGram word embedding models with negative sampling, or SGN in short, is an elegant family of word embedding models.
Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations
The idea of using multi-task learning approaches to address the joint extraction of entity and relation is motivated by the relatedness between the entity recognition task and the relation classification task.
Ranked #8 on
Relation Extraction
on WebNLG
Aggregated Learning: A Vector-Quantization Approach to Learning Neural Network Classifiers
We show that IB learning is, in fact, equivalent to a special class of the quantization problem.
Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree
We propose a method based on neural networks to identify the sentiment polarity of opinion words expressed on a specific aspect of a sentence.
MixUp as Directional Adversarial Training
We prove that the family of Untied MixUp schemes is equivalent to the entire class of DAT schemes.
Augmenting Data with Mixup for Sentence Classification: An Empirical Study
Mixup, a recent proposed data augmentation method through linearly interpolating inputs and modeling targets of random samples, has demonstrated its capability of significantly improving the predictive accuracy of the state-of-the-art networks for image classification.
Understanding Feature Selection and Feature Memorization in Recurrent Neural Networks
Gated models resolve this conflict by adaptively adjusting their state-update equations, whereas Vanilla RNN resolves this conflict by assigning different dimensions different tasks.
Syntax Encoding with Application in Authorship Attribution
We propose a novel strategy to encode the syntax parse tree of sentence into a learnable distributed representation.
MixUp as Locally Linear Out-Of-Manifold Regularization
To address this issue, we propose a novel adaptive version of MixUp, where the mixing policies are automatically learned from the data using an additional network and objective function designed to avoid manifold intrusion.
The APVA-TURBO Approach To Question Answering in Knowledge Base
In this paper, we study the problem of question answering over knowledge base.
Aggregated Learning: A Deep Learning Framework Based on Information-Bottleneck Vector Quantization
Based on the notion of information bottleneck (IB), we formulate a quantization problem called "IB quantization".
Prototypical Recurrent Unit
For this purpose, we design a simple and controllable task, called ``memorization problem'', where the networks are trained to memorize certain targeted information.
On the representation and embedding of knowledge bases beyond binary relations
The models developed to date for knowledge base embedding are all based on the assumption that the relations contained in knowledge bases are binary.
