Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Huazhu SongSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works267 from public data
- 1,345
- Lexical Normalisation of Short Text Messages: Makn Sens a #twitter583
This paper targets out-of-vocabulary words in short text messages and proposes a method for identifying and normalising ill-formed words, which achieves state- of-the-art performance over an SMS corpus and a novel dataset based on Twitter.
- DeepInception: Hypnotize Large Language Model to Be Jailbreaker438
A lightweight method to take advantage of the LLMs' personification capabilities to construct $\textit{a virtual, nested scene}$, allowing it to realize an adaptive way to escape the usage control in a normal scenario.
- Text-Based Twitter User Geolocation Prediction323
This paper presents an integrated geolocation prediction framework, and evaluates the impact of nongeotagged tweets, language, and user-declared metadata on geolocated prediction, and discusses how users differ in terms of their geolocatability.
- Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning298
This paper introduces an intermediate class to avoid directly estimating the noisy class posterior of the transition matrix, and introduces the dual $T-estimator for estimating transition matrices, leading to better classification performances.
- Shared Tasks of the 2015 Workshop on Noisy User-generated Text: Twitter Lexical Normalization and Named Entity Recognition232
The task, annotation process and dataset statistics are outlined, and a high-level overview of the participating systems for each shared task is provided.
- Geolocation Prediction in Social Media Data by Finding Location Indicative Words217
This paper shows that an information gain ratiobased approach surpasses other methods at LIW selection, outperforming state-of-the-art geolocation prediction methods by 10.6% in accuracy and reducing the mean and median of prediction error distance on a public dataset.
- Automatically Constructing a Normalisation Dictionary for Microblogs201
This paper proposes a method for constructing a dictionary of lexical variants of known words that facilitates lexical normalisation via simple string substitution and shows that a dictionary-based approach achieves state-of-the-art performance for both F-score and word error rate on a standard dataset.
- Lexical normalization for social media text197
This article targets out-of-vocabulary words in short text messages and proposes a method for identifying and normalizing lexical variants, which achieves state- of-the-art performance over an SMS corpus and a novel dataset based on Twitter.
- 172
- 148
- 136
- Searching to Exploit Memorization Effect in Learning with Noisy Labels124
This paper designs a domain-specific search space based on general patterns of the memorization effect and proposes a novel Newton algorithm to solve the bi-level optimization problem ef ficiently and provides theoretical analysis of the algorithm, which ensures a good approximation to critical points.
- 116
- Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation100
The proposed manifold-regularized technique works by directly reducing the estimation error without hurting the approximation error about the estimation problem of T(x), and demonstrates that the method is superior to state-of-the-art approaches for label-noise learning under the challenging IDN.
- 92
- Understanding Robust Overfitting of Adversarial Training and Beyond90
The causes of robust overfitting are explored by comparing the data distribution of non-overfit and strong adversary adversarial training, and it is identified that some small-loss data which are not worthy of the adversary strength cause robust over fitting in the strong adversary mode.
- 85
- 81
- Device-Cloud Collaborative Learning for Recommendation78
This work is among the first attempts to study the Device-Cloud Collaborative Learning (DCCL) framework and proposes a novel MetaPatch learning approach on the device side to efficiently achieve "thousands of people with thousands of models'' given a centralized cloud model.
- Harnessing Out-Of-Distribution Examples via Augmenting Content and Style70
A HOOD method that can leverage the content and style from each image instance to identify benign and malign OOD data is proposed, and the proposed novel disentanglement and data augmentation techniques can effectively deal with OOD examples in unknown and open environments.
- 69
- A Stacking-based Approach to Twitter User Geolocation Prediction68
This work implements a city-level geolocation prediction system for Twitter users and suggests that user-declared location metadata is more sensitive to temporal change than the text of Twitter messages.
- Out-of-distribution Detection with Implicit Outlier Transformation65
This work proposes a novel OE-based approach that makes the model perform well for unseen OOD situations, even forseen OOD cases, and offers an efficient way of synthesizing OOD data, which can further benefit the detection model, besides the surrogate Ood data.
- Parts-dependent Label Noise: Towards Instance-dependent Label Noise65
Empirical evaluations demonstrate this method is superior to the state-of-the-art approaches for learning from the instance-dependent label noise and the transition matrices for parts of the instance are learned by exploiting anchor points.
- 61
- 60
- Bilateral Dependency Optimization54
Experiments show that BiDO achieves the state-of-the-art defense performance for a variety of datasets, classifiers, and MI attacks while suffering a minor classification-accuracy drop compared to the well-trained classifier with no defense, which lights up a novel road to defend against MI attacks.
- 53
- 53
- BadLabel: A Robust Perspective on Evaluating and Enhancing Label-Noise Learning49
A robust LNL method is proposed that perturbs the labels in an adversarial manner at each epoch to make the loss values of clean and noisy labels again distinguishable and effectively improve the generalization performance of the model under various types of label noise.
- 47
- Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization46
This work proposes SharpDRO, which exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains by penalizing the sharpness of the worst-case distribution, which measures the loss changes around the neighbor of learning parameters.
- Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score45
This paper proposes a new statistic called expected perturbation score (EPS), which is essentially the expected score of a sample after various perturbations, and theoretically proves that EPS is a proper statistic to compute the discrepancy between two samples under mild conditions.
- Identifying Diseases, Drugs, and Symptoms in Twitter41
The manual annotation results show that it is possible to perform high-quality annotation despite of the complexity of medical terminology and the lack of context in a tweet, and the capability of state-of-the-art approaches to reproduce the annotations in the data set is evaluated.
- 35
- Hard Sample Matters a Lot in Zero-Shot Quantization34
HAST pays more attention to hard samples when synthesizing samples and makes synthetic samples hard to fit when training quantized models, achieving performance comparable to models that are quantized with real data.
- Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model34
This paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances, and can be realized by DNNs, where the training procedure is accomplished by employing a novel alternating optimization algorithm.
- 33
- 33
- How Does Disagreement Benefit Co-teaching?32
Empirical results on noisy versions of MNIST, CIFAR-10 and NEWS demonstrate that Co-teaching+ is much superior to the state-of-the-art methods in the robustness of trained deep models.
- 31
- 31
- 31
- FedImpro: Measuring and Improving Client Update in Federated Learning28
FedImpro decouples the model into high-level and low-level components, and trains the high-level portion on reconstructed feature distributions that enhances the generalization contribution and reduces the dissimilarity of gradients in FL.
- Extended : Learning with Mixed Closed-set and Open-set Noisy Labels28
The traditional transition matrix is extended to be able to model mixed label noise, and further to the cluster-dependent extended transition matrix to better combat the instance-dependent label noise in real-world applications.
- 27
- 27
- Tackling Noisy Labels With Network Parameter Additive Decomposition26
To decouple the memorization of clean data and mislabeled data, and further reduce the side effect of mislabeled data, additive decomposition on network parameters is performed.
- Regularly Truncated M-Estimators for Learning With Noisy Labels26
Regular truncated M-estimators (RTME) is proposed, which can alternately switch modes between truncated M-estimators and original M-estimators and is robust to broad noise types and levels.
- Improving Adversarial Robustness via Mutual Information Estimation26
This paper investigates the dependence between outputs of the target model and input adversarial samples from the perspective of information theory, and proposes an adversarial defense method that could effectively improve the adversarial accuracy against multiple attacks.
- FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels25
A simple two-level sampling method that selects clean labels and correct pseudo-labels at the client end for more robust local training and investigates different schedules changing the local epochs between aggregations over the course of FL, which notably improves the communication and computation efficiency in noisy label setting.
- 25
- 25
- 24
- 24
- 23
- Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations23
An efficient solver that avoids expensive tensor folding and unfolding is developed based on the proximal average algorithm and is also more accurate than existing approaches.
- 23
- Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability22
A novel method is proposed, Unleashing Mask, which aims to restore the OOD discriminative capabilities of the well-trained model with ID data by utilizing a mask to figure out the memorized atypical samples, and then finetune the model or prune it with the introduced mask to forget them.
- 22
- 21
- 21
- 21
- 21
- Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalization20
By fully exploring both variant and invariant parameters, the EVIL can effectively identify a robust subnetwork to improve OOD generalization and can effectively and efficiently enhance many popular methods, such as ERM, IRM, SAM, etc.
- 20
- 20
- 20
- 20
- 20
- 20
- 19
- 19
- 19
- 19
- 18
- 17
- 17
- 17
- Pumpout: A Meta Approach for Robustly Training Deep Neural Networks with Noisy Labels17
A meta algorithm called Pumpout is proposed to overcome the problem of memorizing noisy labels by using scaled stochastic gradient ascent, which actively squeezes out the negative effects of noisy labels from the training model, instead of passively forgetting these effects.
- Co-sampling: Training Robust Networks for Extremely Noisy Supervision17
Free of the matrix estimation, a simple but robust learning paradigm called "Co-sampling" is presented, which can train deep networks robustly under extremely noisy labels and demonstrates that it trains deep learning models robustly.
- Structural damage detection by integrating independent component analysis and support vector machine17
- 16
- 16
- 15
- 15
- 15
- 15
- Maximum Mean Discrepancy is Aware of Adversarial Attacks15
It is validated that MMD is aware of adversarial attacks, which lights up a novel road for adversarial attack detection based on two-sample tests.
- 15
- 14
- 14
- 14
- 14
- 13
- 13
- 13
- 13
- 13
- 13
- 12
- 12
- Robust Plackett–Luce model for k-ary crowdsourced preferences12
This paper presents a RObust PlAckett–Luce (ROPAL) model, and proposes an online Bayesian inference to make ROPAL scalable to large-scale preferences and achieves substantial improvements in robustness and noisy worker detection over current approaches.
- 12
- Alignclip: navigating the misalignments for robust vision-language generalization11
AlignCLIP is proposed, an advanced fine-tuning methodology distinguished by its attention alignment loss, designed to calibrate the distribution of attention across multi-head attention layers and introduces semantic label smoothing, a technique that leverages textual class similarities to refine prediction hierarchies.
- 11
- 11
- Learning with Group Noise11
This work proposes a novel Max-Matching method for learning with group noise that utilizes a matching mechanism to evaluate the relation confidence of each object w.r.t. the target, which considers the Non-IID characteristics among objects in the group.
- Towards Mixture Proportion Estimation without Irreducibility.11
This paper builds a new irreducible MPE problem and solves the new problem, and proposes Regrouping-MPE, a method that outperforms all state-of-the-art MPE methods on various real-world datasets.
- Combating Exacerbated Heterogeneity for Robust Models in Federated Learning10
A novel framework called Slack Federated Adversarial Training (SFAT), assigning the client-wise slack during aggregation to combat the intensified heterogeneity among local clients and properly relax the objective when combining federated learning and adversarial training is proposed.
- 10
- 10
- 10
- 10
- Learning a robust foundation model against clean-label data poisoning attacks at downstream tasks9
This work proposes a defense strategy that significantly reduces the success rate of various data poisoning attacks in downstream tasks and aims to pre-train a robust foundation model by reducing adversarial feature distance and increasing inter-class feature distance.
- 9
- 9
- 9
- 9
- 8
- 8
- A Universal Unbiased Method for Classification from Aggregate Observations8
The goal of this paper is to present a novel universal method of CFAO, which holds an unbiased estimator of the classification risk for arbitrary losses -- previous research failed to achieve this goal.
- 8
- 8
- 8
- Strength-Adaptive Adversarial Training7
A novel technique called Strength-Adaptive Adversarial Training (SAAT), which incorporates an adversarial-loss constraint to guide the generation of adversarial training data and substantially improves adversarial robustness over standard AT.
- Defending Against Adversarial Examples Via Modeling Adversarial Noise7
This work constructs an instance-dependent label transition matrix to represent the label transition relationship for explicitly modeling adversarial noise and designs an adversarial robustness constraint at the transition matrix level to enhance the robustness of the label transition network.
- W-DOE: Wasserstein Distribution-Agnostic Outlier Exposure7
This work proposes a novel OE-based learning method termed Wasserstein Distribution-agnostic Outlier Exposure (W-DOE), which is both theoretically sound and experimentally superior to previous works, and suggests a general learning framework to search for the synthesized OOD data that can benefit the models most, ensuring the OOD performance for the enlarged OOD coverage measured by the Wasserstein metric.
- 7
- 7
- Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation7
A diversity-enhancing generative network (DEG-Net) is proposed for the FHA problem, which can generate diverse unlabeled data with the help of a kernel independence measure: the Hilbert-Schmidt independence criterion (HSIC).
- Towards Lightweight Black-Box Attacks against Deep Neural Networks7
It is argued that black-box attacks can pose practical attacks in this extremely restrictive scenario where only several test samples are available and the proposed Error TransFormer (ETF) transforms the approximation error in the parameter space into a perturbation in the feature space and alleviates the error by disturbing features.
- 7
- 7
- Pumpout: A Meta Approach to Robust Deep Learning with Noisy Labels7
Pumpout is proposed as a meta approach to learning with noisy labels and an alternative to early stopping, and it is demonstrated via experiments that Pumpout robustifies two representative base learning methods, and the performance boost is often significant.
- 6
- 6
- 6
- 6
- 6
- 6
- USN: A Robust Imitation Learning Method against Diverse Action Noise5
A robust learning paradigm called USN (Uncertainty-aware Sample-selection with Negative learning), which first estimates the predictive uncertainty for all demonstration data and then selects samples with high loss based on the uncertainty measures based on the uncertainty measures.
- 5
- MSR: Making Self-supervised learning Robust to Aggressive Augmentations5
This work proposes a new SSL paradigm, which counteracts the impact of semantic shift by balancing the role of weak and aggressively augmented pairs, and can better embrace the aggressive augmentations and neutralize the semantic shift problem.
- 5
- 5
- 5
- Stagewise learning for noisy k-ary preferences5
A reliable CrowdsOUrced Plackett–LucE (COUPLE) model combined with an efficient Bayesian learning technique is proposed, which achieves substantial improvements in reliability and noisy worker detection over other well-known approaches.
- Millionaire: a hint-guided approach for crowdsourcing5
This paper introduces the hint-guided approach into crowdsourcing, motivated by the “Guess-with-Hints” answer strategy from the Millionaire game show, and proposes a hybrid-stage setting, consisting of the main stage and the hint stage.
- 5
- Research on optimization and parallelization of Optimal Binary Search Tree using Dynamic Programming5
- 5
- Unknown-Aware Bilateral Dependency Optimization for Defending Against Model Inversion Attacks4
The bilateral dependency optimization strategy (BiDO) is proposed, a dual-objective approach that minimizes the dependency between input features and latent representations, while simultaneously maximizing the dependency between latent representations and labels.
- 4
- 4
- MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence4
A bi-level optimization framework to learn a set of class-specific representations that match the cluster structures indicated by labeled data of the given task, and can not only achieve better generalization performance on unseen domains in most cases but also learn better data representation clusters.
- 4
- Making Binary Classification from Multiple Unlabeled Datasets Almost Free of Supervision4
This work proposes a novel framework to handle the MU-OPPO problem, which consists of four sequential modules: (i) pseudo label assignment; (ii) confident example collection; (iii) class prior estimation; (iv) classifier training with estimated class priors.
- Learning and Mining with Noisy Labels4
This tutorial summarizes the foundations and goes through the most recent noisy-label-tolerant techniques, and the audience will gain a broad knowledge of learning and mining with noisy labels from the viewpoint of statistical learning theory, deep learning, detailed analysis of typical algorithms and frameworks, and their real-world data mining applications.
- 4
- 4
- Collaborative Attention Network with Word and N-Gram Sequences Modeling for Sentiment Classification4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- Exploit CAM by itself: Complementary Learning System for Weakly Supervised Semantic Segmentation3
The Seed Reactivation to help SLM reactivate non-discriminating regions by setting a boundary for activation values, which successively identifies more regions of CAM is proposed, representing a new state-of-the-art among existing WSSS methods.
- Pluralistic Image Completion with Probabilistic Mixture-of-Experts3
A unified probabilistic graph model is introduced that represents the complex interactions in image completion and is formally established the effectiveness of the method and demonstrated it with comprehensive experiments.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- Enhancing Neural Subset Selection: Integrating Background Information into Set Representations2
This work proposes a simple yet effective information aggregation module designed to merge the representations of subsets and supersets from a permutation invariance perspective, underscoring the practicality and potency of the proposed strategies in real-world contexts.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- Improving the Instance-Dependent Transition Matrix Estimation by Exploiting Self-Supervised Learning1
- 1
- 1
- Slack Federated Adversarial Training1
This work introduces an <inline-formula>-slack mechanism to relax the original learning objective of federated adversarial training, and proposes a novel framework called SFAT (SFAT) to combat the intensified heterogeneity.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Exploring Model Dynamics for Accumulative Poisoning Discovery–
This paper dives into the perspective of model dynamics and proposes a novel information measure, namely, Memorization Discrepancy, to explore the defense via the model-level information and proposes Discrepancies-aware Sample Correction (DSC) to defend against accumulative poisoning attacks.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.