Author name cluster

Ximing Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

33 papers

2 author rows

AAAI Conference 2026 Conference Paper

Denoising Mixup for Regression

Zhengzhang Hou
Zhanshan Li
Yanbo Liu
Geoff Nitschke
You Lu
Ximing Li

Data augmentation is an intuitive solution to increase the diversity of training instances in the machine learning community. Mixup is acknowledged as an effective and efficient mix-based data augmentation method, following a linear alignment assumption that the linear interpolations of features align the corresponding linear interpolations of labels. Unfortunately, this assumption can be violated in many complex scenarios, resulting in augmented instances with noisy labels, especially for regression problems. To solve this problem, we propose an easy-to-implement mixup method, namely DEnosing MIXUP (DE-mixup), which iteratively corrects the noisy response targets by leveraging an auxiliary noise estimation task with mixup deep features. Additionally, we suggest an efficient optimization method with alternating direction method of multipliers. We compare DE-mixup with the existing mixup variants and other prevalent data augmentation methods across benchmark regression datasets. Empirical results indicate the effectiveness of DE-mixup under the in-distribution and out-of-distribution cases.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective

Bing Wang
Ximing Li
Yanjun Wang
Changchun Li
Lin Yuanbo Wu
Buyu Wang
Shengsheng Wang

Multimodal Misinformation Detection (MMD) refers to the task of detecting social media posts involving misinformation, where the post often contains text and image modalities. However, by observing the MMD posts, we hold that the text modality may be much more informative than the image modality because the text generally describes the whole event/story of the current post but the image often presents partial scenes only. Our preliminary empirical results indicate that the image modality exactly contributes less to MMD. Upon this idea, we propose a new MMD method named RETSIMD. Specifically, we suppose that each text can be divided into several segments, and each text segment describes a partial scene that can be presented by an image. Accordingly, we split the text into a sequence of segments, and feed these segments into a pre-trained text-to-image generator to augment a sequence of images. We further incorporate two auxiliary objectives concerning text-image and image-label mutual information, and further post-train the generator over an auxiliary text-to-image generation benchmark dataset. Additionally, we propose a graph structure by defining three heuristic relationships between images, and use a graph neural network to generate the fused features. Extensive empirical results validate the effectiveness of RETSIMD.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Semi-Supervised Regression by Preserving Ranking Relationships Between Close Unlabeled Samples

Ximing Li
Jiaxuan Jiang
Changchun Li
You Lu
Renchu Guan

Semi-Supervised Learning (SSL) aims to improve the learning performance of supervised learning with a large number of unlabeled samples. The existing SSL methods such as FixMatch and FlexMatch select unlabeled samples with high-confident pseudo-labels and make consistency constraints between their weak and strong augmentations. Unfortunately, they cannot be applied Semi-Supervised Regression (SSR) because regression predictions can not reflect the confidence of pseudo-labels. To solve this, a recent SSR method RankUp incorporates an auxiliary ranking task by leveraging sample pairs with high-confident pseudo-ranks. In this paper, we upgrade Rankup to a novel SSR method, namely Semi-Supervised Regression by Ranking Close Unlabeled Samples (SSR-RCUS). Its basic idea is reconstructing closed mixup augmented samples with high-confident pseudo-ranks under a monotonicity assumption, and then applying them to the auxiliary ranking task to improve regression performance. We conduct extensive experiments to evaluate the performance of SSR-RCUS on benchmark datasets, and empirical results demonstrate that SSR-RCUS can outperform the existing baselines in various settings, especially when labeled data are scarce.

PDF Details DOI

AAAI Conference 2026 Conference Paper

SPARD: Single-step Inference with Adaptive Sampling in Residual Diffusion for Human Motion Prediction

Yiming Zhang
Baojia Han
Ximing Li
Wei Pang
Fausto Giunchiglia
Xiaoyue Feng
Renchu Guan

The task of stochastic human motion prediction has attracted significant attention in recent years due to its wide-ranging applications in robotics, animation, and human-computer interaction. While diffusion models have demonstrated promising progress in this domain, they remain hindered by two critical limitations: (1) slow inference speeds due to their reliance on iterative sampling, and (2) performance degradation resulting from suboptimal sample allocation during generation. To overcome these challenges, we propose SPARD (Single-step Inference with Adaptive Sampling in Residual Diffusion for Human Motion Prediction), a novel framework that achieves efficient single-step inference while maintaining high predictive accuracy. Furthermore, we introduce a novel adaptive noise predictor module that dynamically samples latent representations based on observed motion sequences, ensuring both accuracy and plausibility in generated motions. Extensive experiments on benchmark datasets demonstrate that SPARD significantly outperforms state-of-the-art methods in both inference efficiency and motion quality, achieving a 15× to 18× speedup in sampling time compared to conventional diffusion-based baselines while preserving generation quality.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

A Closer Look to Positive-Unlabeled Learning from Fine-grained Perspectives: An Empirical Study

Yuanchao Dai
Zhengzhang Hou
Changchun Li
Yuanbo Xu
En Wang
Ximing Li

Positive-Unlabeled (PU) learning refers to a specific weakly-supervised learning paradigm that induces a binary classifier with a few positive labeled instances and massive unlabeled instances. To handle this task, the community has proposed dozens of PU learning methods with various techniques, demonstrating strong potential. In this paper, we conduct a comprehensive study to investigate the basic characteristics of current PU learning methods. We organize them into two fundamental families of PU learning, including disambiguation-free empirical risks, which approximate the expected risk of supervised learning, and pseudo-labeling methods, which estimate pseudo-labels for unlabeled instances. First, we make an empirical analysis on disambiguation-free empirical risks such as uPU, nnPU, and DistPU, and suggest a novel risk-consistent set-aware empirical risk from the perspective of aggregate supervision. Second, we make an empirical analysis of pseudo-labeling methods to evaluate the potential of pseudo-label estimation techniques and widely applied generic tricks in PU learning. Finally, based on those empirical findings, we propose a general framework of PU learning by integrating the set-aware empirical risk with pseudo-labeling. Compared with existing PU learning methods, the proposed framework can be a practical benchmark in PU learning.

PDF Details

EAAI Journal 2025 Journal Article

A multi-agent deep reinforcement learning method for fully noisy observations

Kaiyu Wang
Danni Wang
Bohao Qu
Menglin Zhang
Xianchang Wang
Ximing Li

Multi-agent reinforcement learning (MARL) algorithms have achieved great breakthroughs in many aspects. The MARL algorithms can learn effective policies in ideal simulation environments. But different from the ideal simulation environments, noise is unavoidable in the real world. MARL algorithms need to learn effective policies in unavoidable fully noisy environments. In this paper, we consider a challenging multi-agent reinforcement learning problem: All agents cannot observe any noiseless observations from environments during the whole training process and MARL algorithms cannot learn effective policies in these fully noisy observation environments. To solve this problem, we propose a method called Robust P olicy L earning under Fully Noisy Observation vi A De N oising R E presentation Ne T work (PLANET), which enables MARL algorithms learning effective policies in fully noisy observation environments. The PLANET method learns the effective policy through two steps. (1) Extracting the noise characteristics and motion laws to obtain clean observations information from fully noisy observation histories. (2) Making MARL algorithms extract information from the noise characteristics and motion laws information, and learn effective policies. The results of a series of exhaustive experiments show that our method can mitigate the effects of noise and learn effective policies in fully noisy observation environments. Our Artificial Intelligence contribution lies in introducing the denoising representation network that learns noise characteristics and motion dynamics to recover clean observations from fully noisy observations. The proposed PLANET framework could be applied to real-world multi-agent robotic and sensor network systems, potentially improving policy robustness under fully noisy observation.

Details DOI

AAAI Conference 2025 Conference Paper

A Simple Graph Contrastive Learning Framework for Short Text Classification

Yonghao Liu
Fausto Giunchiglia
Lan Huang
Ximing Li
Xiaoyue Feng
Renchu Guan

Short text classification has gained significant attention in the information age due to its prevalence and real-world applications. Recent advancements in graph learning combined with contrastive learning have shown promising results in addressing the challenges of semantic sparsity and limited labeled data in short text classification. However, existing models have certain limitations. They rely on explicit data augmentation techniques to generate contrastive views, resulting in semantic corruption and noise. Additionally, these models only focus on learning the intrinsic consistency between the generated views, neglecting valuable discriminative information from other potential views. To address these issues, we propose a Simple graph contrastive learning framework for Short Text Classification (SimSTC). Our approach involves performing graph learning on multiple text-related component graphs to obtain multi-view text embeddings. Subsequently, we directly apply contrastive learning on these embeddings. Notably, our method eliminates the need for data augmentation operations to generate contrastive views while still leveraging the benefits of multi-view contrastive learning. Despite its simplicity, our model achieves outstanding performance, surpassing large language models on various datasets.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Balancing Positive and Negative Classification Error Rates in Positive-Unlabeled Learning

Ximing Li
Yuanchao Dai
Bing Wang
Changchun Li
Jianfeng Qu
Renchu Guan

Positive and Unlabeled (PU) learning is a special case of binary classification with weak supervision, where only positive labeled and unlabeled data are available. Previous studies suggest several specific risk estimators of PU learning such as non-negative PU (nnPU), which are unbiased and consistent with the expected risk of supervised binary classification. In nnPU, the negative-class empirical risk is estimated by positive labeled and unlabeled data with a non-negativity constraint. However, its negative-class empirical risk estimator approaches 0, so the negative class is over-played, resulting in imbalanced error rates between positive and negative classes. To solve this problem, we suppose that the expected risks of the positive-class and negative-class should be close. Accordingly, we constrain that the negative-class empirical risk estimator is lower bounded by the positive-class empirical risk, instead of 0; and also incorporate an explicit equality constraint between them. we suggest a risk estimator of PU learning that balances positive and negative classification error rates, named $\mathrm{D{\small C-PU} }$, and suggest an efficient training method for $\mathrm{D{\small C-PU} }$ based on the augmented Lagrange multiplier framework. We theoretically analyze the estimation error of $\mathrm{D{\small C-PU} }$ and empirically validate that $\mathrm{D{\small C-PU} }$ achieves higher accuracy and converges more stable than other risk estimators of PU learning. Additionally, $\mathrm{D{\small C-PU} }$ also performs competitive accuracy performance with practical PU learning methods.

PDF Details

NeurIPS Conference 2025 Conference Paper

Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibration

Yonghao Liu
Yajun Wang
Chunli Guo
Wei Pang
Ximing Li
Fausto Giunchiglia
Xiaoyue Feng
Renchu Guan

Graph few-shot learning has attracted increasing attention due to its ability to rapidly adapt models to new tasks with only limited labeled nodes. Despite the remarkable progress made by existing graph few-shot learning methods, several key limitations remain. First, most current approaches rely on predefined and unified graph filters (e. g. , low-pass or high-pass filters) to globally enhance or suppress node frequency signals. Such fixed spectral operations fail to account for the heterogeneity of local topological structures inherent in real-world graphs. Moreover, these methods often assume that the support and query sets are drawn from the same distribution. However, under few-shot conditions, the limited labeled data in the support set may not sufficiently capture the complex distribution of the query set, leading to suboptimal generalization. To address these challenges, we propose GRACE, a novel Graph few-shot leaRning framework that integrates Adaptive spectrum experts with Cross-sEt distribution calibration techniques. Theoretically, the proposed approach enhances model generalization by adapting to both local structural variations and cross-set distribution calibration. Empirically, GRACE consistently outperforms state-of-the-art baselines across a wide range of experimental settings. Our code can be found here.

PDF Details

AAAI Conference 2025 Conference Paper

Learning Causal Transition Matrix for Instance-dependent Label Noise

Jiahui Li
Tai-Wei Chang
Kun Kuang
Ximing Li
Long Chen
Jun Zhou

Noisy labels are both inevitable and problematic in machine learning methods, as they negatively impact models' generalization ability by causing overfitting. In the context of learning with noise, the transition matrix plays a crucial role in the design of statistically consistent algorithms. However, the transition matrix is often considered unidentifiable. One strand of methods typically addresses this problem by assuming that the transition matrix is instance-independent; that is, the probability of mislabeling a particular instance is not influenced by its characteristics or attributes. This assumption is clearly invalid in complex real-world scenarios. To better understand the transition relationship and relax this assumption, we propose to study the data generation process of noisy labels from a causal perspective. We discover that an unobservable latent variable can affect either the instance itself, the label annotation procedure, or both, which complicates the identification of the transition matrix. To address various scenarios, we have unified these observations within a new causal graph. In this graph, the input instance is divided into a noise-resistant component and a noise-sensitive component based on whether they are affected by the latent variable. These two components contribute to identifying the “causal transition matrix”, which approximates the true transition matrix with theoretical guarantee. In line with this, we have designed a novel training framework that explicitly models this causal relationship and, as a result, achieves a more accurate model for inferring the clean label.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Robust Misinformation Detection by Visiting Potential Commonsense Conflict

Bing Wang
Ximing Li
Changchun Li
Bingrui Zhao
Bo Fu
Renchu Guan
Shengsheng Wang

The development of Internet technology has led to an increased prevalence of misinformation, causing severe negative effects across diverse domains. To mitigate this challenge, Misinformation Detection (MD), aiming to detect online misinformation automatically, emerges as a rapidly growing research topic in the community. In this paper, we propose a novel plug-and-play augmentation method for the MD task, namely Misinformation Detection with Potential Commonsense Conflict (MD-PCC). We take inspiration from the prior studies indicating that fake articles are more likely to involve commonsense conflict. Accordingly, we construct commonsense expressions for articles, serving to express potential commonsense conflicts inferred by the difference between extracted commonsense triplet and golden ones inferred by the well-established commonsense reasoning tool COMET. These expressions are then specified for each article as augmentation. Any specific MD methods can be then trained on those commonsense-augmented articles. Besides, we also collect a novel commonsense-oriented dataset named CoMis, whose all fake articles are caused by commonsense conflict. We integrate MD-PCC with various existing MD backbones and compare them across both 4 public benchmark datasets and CoMis. Empirical results demonstrate that MD-PCC can consistently outperform the existing MD baselines.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Utterance-level Emotion Recognition in Conversation with Conversation-level Supervision

Ximing Li
Yuanchao Dai
Zhiyao Yang
Jinjin Chi
Wanfu Gao
Lin Yuanbo Wu

Emotion Recognition in Conversations (ERC) involves automatically identifying the emotion of each utterance in conversations. The emotion of an utterance is contingent to the conversation context, and thus, annotating each utterance in ERC entails repetitive screening the whole conversation from annotators. Such a requirement leads to prohibitive cost in fine-grained labeling on utterance. In this paper, we propose an efficient coarse-grained labeling strategy for ERC, which assigns a set of emotions for each conversation. In specific, we reformulate the ERC predictors with conversation-level emotion sets as weakly-supervised learning to optimise a potential candidate for ERC, which is termed as Dataless ERC (DERC). To validate this, we propose a simple-yet-flexible DERC framework with Progressive Learning (DERC-PL). We jointly update pseudo-utterance-level emotions and the ERC predictor in a self-training manner, where we progressively update the ERC predictor from training subsets with lower noise densities to the ones with higher noise densities. We implemented several versions of \baby by incorporating various off-the-shelf ERC methods. Extensive experimental results demonstrate that the proposed \baby can be on par with existing weakly-supervised learning baselines and supervised learning ERC methods.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Alleviating Imbalanced Pseudo-label Distribution: Self-Supervised Multi-Source Domain Adaptation with Label-specific Confidence

Shuai Lü
Meng Kang
Ximing Li

The existing self-supervised Multi-Source Domain Adaptation (MSDA) methods often suffer an imbalanced characteristic among the distribution of pseudo-labels. Such imbalanced characteristic results in many labels with too many or too few pseudo-labeled samples on the target domain, referred to as easy-to-learn label and hard-to-learn label, respectively. Both of these labels hurt the generalization performance on the target domain. To alleviate this problem, in this paper we propose a novel multi-source domain adaptation method, namely Self-Supervised multi-Source Domain Adaptation with Label-specific Confidence (S3DA-LC). Specifically, we estimate the label-specific confidences, i. e. , the learning difficulties of labels, and adopt them to generate the pseudo-labels for target samples, enabling to simultaneously constrain and enrich the pseudo supervised signals for easy-to-learn and hard-to-learn labels. We evaluate S3DA-LC on several benchmark datasets, indicating its superior performance compared with the existing MSDA baselines.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations

Jihong Ouyang
Zhiyao Yang
Silong Liang
Bing Wang
Yimeng Wang
Ximing Li

Aspect-based sentiment analysis (ABSA), a fine-grained sentiment classification task, has received much attention recently. Many works investigate sentiment information through opinion words, such as "good'' and "bad''. However, implicit sentiment data widely exists in the ABSA dataset, whose sentiment polarity is hard to determine due to the lack of distinct opinion words. To deal with implicit sentiment, this paper proposes an ABSA method that integrates explicit sentiment augmentations (ABSA-ESA) to add more sentiment clues. We propose an ABSA-specific explicit sentiment generation method to create such augmentations. Specifically, we post-train T5 by rule-based data and employ three strategies to constrain the sentiment polarity and aspect term of the generated augmentations. We employ Syntax Distance Weighting and Unlikelihood Contrastive Regularization in the training procedure to guide the model to generate the explicit opinion words with the same polarity as the input sentence. Meanwhile, we utilize the Constrained Beam Search to ensure the augmentations are aspect-related. We test ABSA-ESA on two ABSA benchmarks. The results show that ABSA-ESA outperforms the SOTA baselines on implicit and explicit sentiment accuracy.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning

Jiaan Wang
Jianfeng Qu
Kexin Wang
Zhixu Li
Wen Hua
Ximing Li
An Liu

Knowledge-grounded dialogue (KGD) learns to generate an informative response based on a given dialogue context and external knowledge (e.g., knowledge graphs; KGs). Recently, the emergence of large language models (LLMs) and pre-training techniques has brought great success to knowledge-grounded dialogue. However, when building KGD systems in real applications, there are various real-world noises that are inevitable to face. For example, the dialogue context might involve perturbations such as misspellings and abbreviations. In addition, KGs typically suffer from incompletion and also might contain erroneous and outdated facts. Such real-world noises pose a challenge to the robustness of KGD systems and hinder their applications in the real world. In this paper, we propose an entity-based contrastive learning framework for improving the robustness of KGD. Specifically, we make use of the entity information in a KGD sample to create both its positive and negative samples which involve semantic-irrelevant and semantic-relevant perturbations, respectively. The contrastive learning framework ensures the KGD model is aware of these two types of perturbations, thus could generate informative responses with the potentially noisy inputs in real applications. Experimental results on three widely-used benchmark datasets show that our method achieves new state-of-the-art performance in terms of automatic evaluation scores, verifying its effectiveness and potentiality. Furthermore, we show that our method is able to generate better responses than comparison models in both the noisy and the few-shot settings.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Nukplex: An Efficient Local Search Algorithm for Maximum K-Plex Problem

Rui Sun
Yiyuan Wang
Shimao Wang
Hui Li
Ximing Li
Minghao Yin

The maximum k-plex problem (MKPP) is an significant relaxation version of the maximum clique problem with extensive applications. Recently, lots of researchers have proposed many heuristic algorithms based on various methods to solve the MKPP. In this work, to further improve the performance of solving the MKPP, we propose an efficient local search algorithm based on three main ideas. First, we propose a relaxed bounded configuration checking strategy that considers two kinds of historical searching information to relax the restricted strength of configuration checking and the forbidden condition of candidate vertices for the operation Add, respectively. Second, we present a novel solution information-based vertex selection strategy based on two kinds of solution information to select high-quality candidate vertices. Third, we define the solution core and then introduce a core-based perturbation strategy to help the algorithm jump out of local optima. The experimental results show that the proposed algorithm significantly outperforms the state-of-the-art MKPP algorithms in almost all the instances.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Resolving Word Vagueness with Scenario-guided Adapter for Natural Language Inference

Yonghao Liu
Mengyu Li
Di Liang
Ximing Li
Fausto Giunchiglia
Lan Huang
Xiaoyue Feng
Renchu Guan

Natural Language Inference (NLI) is a crucial task in natural language processing that involves determining the relationship between two sentences, typically referred to as the premise and the hypothesis. However, traditional NLI models solely rely on the semantic information inherent in independent sentences and lack relevant situational visual information, which can hinder a complete understanding of the intended meaning of the sentences due to the ambiguity and vagueness of language. To address this challenge, we propose an innovative ScenaFuse adapter that simultaneously integrates large-scale pre-trained linguistic knowledge and relevant visual information for NLI tasks. Specifically, we first design an image-sentence interaction module to incorporate visuals into the attention mechanism of the pre-trained model, allowing the two modalities to interact comprehensively. Furthermore, we introduce an image-sentence fusion module that can adaptively integrate visual information from images and semantic information from sentences. By incorporating relevant visual information and leveraging linguistic knowledge, our approach bridges the gap between language and vision, leading to improved understanding and inference capabilities in NLI tasks. Extensive benchmark experiments demonstrate that our proposed ScenaFuse, a scenario-guided approach, consistently boosts NLI performance.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss

Ximing Li
Silong Liang
Changchun Li
Pengfei Wang
Fangming Gu

Semi-supervised multi-label learning (SSMLL) refers to inducing classifiers using a small number of samples with multiple labels and many unlabeled samples. The prevalent solution of SSMLL involves forming pseudo-labels for unlabeled samples and inducing classifiers using both labeled and pseudo-labeled samples in a self-training manner. Unfortunately, with the commonly used binary type of loss and negative sampling, we have empirically found that learning with labeled and pseudo-labeled samples can result in the variance bias problem between the feature distributions of positive and negative samples for each label. To alleviate this problem, we aim to balance the variance bias between positive and negative samples from the perspective of the feature angle distribution for each label. Specifically, we extend the traditional binary angular margin loss to a balanced extension with feature angle distribution transformations under the Gaussian assumption, where the distributions are iteratively updated during classifier training. We also suggest an efficient prototype-based negative sampling method to maintain high-quality negative samples for each label. With this insight, we propose a novel SSMLL method, namely Semi-Supervised Multi-Label Learning with Balanced Binary Angular Margin loss (S$^2$ML$^2$-BBAM). To evaluate the effectiveness of S$^2$ML$^2$-BBAM, we compare it with existing competitors on benchmark datasets. The experimental results validate that S$^2$ML$^2$-BBAM can achieve very competitive performance.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

WPML3CP: Wasserstein Partial Multi-Label Learning with Dual Label Correlation Perspectives

Ximing Li
Yuanchao Dai
Bing Wang
Changchun Li
Renchu Guan
Fangming Gu
Jihong Ouyang

Partial multi-label learning (PMLL) refers to a weakly-supervised classification problem, where each instance is associated with a set of candidate labels, covering its ground-truth labels but also with irrelevant ones. The current methodology of PMLL is to estimate the ground-truth confidences of candidate labels, i. e. , the likelihood of a candidate label being a ground-truth one, and induce the multi-label predictor with them, rather than the candidate labels. In this paper, we aim to estimate precise ground-truth confidences by leveraging precise label correlations, which are also required to estimate. To this end, we propose to capture label correlations from both measuring and modeling perspectives. Specifically, we measure the loss between ground-truth confidences and predictions by employing the Wasserstein distance involving label correlations; and form a label correlation-aware regularization to constraint predictive parameters. The two techniques are coupled to promote precise estimations of label correlations. Upon these ideas, we propose a novel PMLL method, namely Wasserstein Partial Multi-Label Learning with dual Label Correlation Perspectives (WPML3CP). We conduct extensive experiments on several benchmark datasets. Empirical results demonstrate that WPML3CP can outperform the existing PMLL baselines.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Learning with Partial Labels from Semi-supervised Perspective

Ximing Li
Yuanzhi Jiang
Changchun Li
Yiyuan Wang
Jihong Ouyang

Partial Label (PL) learning refers to the task of learning from the partially labeled data, where each training instance is ambiguously equipped with a set of candidate labels but only one is valid. Advances in the recent deep PL learning literature have shown that the deep learning paradigms, e.g., self-training, contrastive learning, or class activate values, can achieve promising performance. Inspired by the impressive success of deep Semi-Supervised (SS) learning, we transform the PL learning problem into the SS learning problem, and propose a novel PL learning method, namely Partial Label learning with Semi-supervised Perspective (PLSP). Specifically, we first form the pseudo-labeled dataset by selecting a small number of reliable pseudo-labeled instances with high-confidence prediction scores and treating the remaining instances as pseudo-unlabeled ones. Then we design a SS learning objective, consisting of a supervised loss for pseudo-labeled instances and a semantic consistency regularization for pseudo-unlabeled instances. We further introduce a complementary regularization for those non-candidate labels to constrain the model predictions on them to be as small as possible. Empirical results demonstrate that PLSP significantly outperforms the existing PL baseline methods, especially on high ambiguity levels. Code available: https://github.com/changchunli/PLSP.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Local and Global: Temporal Question Answering via Information Fusion

Yonghao Liu
Di Liang
Mengyu Li
Fausto Giunchiglia
Ximing Li
Sirui Wang
Wei Wu
Lan Huang

Many models that leverage knowledge graphs (KGs) have recently demonstrated remarkable success in question answering (QA) tasks. In the real world, many facts contained in KGs are time-constrained thus temporal KGQA has received increasing attention. Despite the fruitful efforts of previous models in temporal KGQA, they still have several limitations. (I) They neither emphasize the graph structural information between entities in KGs nor explicitly utilize a multi-hop relation path through graph neural networks to enhance answer prediction. (II) They adopt pre-trained language models (LMs) to obtain question representations, focusing merely on the global information related to the question while not highlighting the local information of the entities in KGs. To address these limitations, we introduce a novel model that simultaneously explores both Local information and Global information for the task of temporal KGQA (LGQA). Specifically, we first introduce an auxiliary task in the temporal KG embedding procedure to make timestamp embeddings time-order aware. Then, we design information fusion layers that effectively incorporate local and global information to deepen question understanding. We conduct extensive experiments on two benchmarks, and LGQA significantly outperforms previous state-of-the-art models, especially in difficult questions. Moreover, LGQA can generate interpretable and trustworthy predictions.

PDF Details DOI

ICLR Conference 2023 Conference Paper

Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms

Ximing Li
Chendi Wang
Guang Cheng 0003

Marginal-based methods achieve promising performance in the synthetic data competition hosted by the National Institute of Standards and Technology (NIST). To deal with high-dimensional data, the distribution of synthetic data is represented by a probabilistic graphical model (e.g., a Bayesian network), while the raw data distribution is approximated by a collection of low-dimensional marginals. Differential privacy (DP) is guaranteed by introducing random noise to each low-dimensional marginal distribution. Despite its promising performance in practice, the statistical properties of marginal-based methods are rarely studied in the literature. In this paper, we study DP data synthesis algorithms based on Bayesian networks (BN) from a statistical perspective. We establish a rigorous accuracy guarantee for BN-based algorithms, where the errors are measured by the total variation (TV) distance or the $L^2$ distance. Related to downstream machine learning tasks, an upper bound for the utility error of the DP synthetic data is also derived. To complete the picture, we establish a lower bound for TV accuracy that holds for every $\epsilon$-DP synthetic data generator.

Details

AAAI Conference 2023 Conference Paper

TC-DWA:Text Clustering with Dual Word-Level Augmentation

Bo Cheng
Ximing Li
Yi Chang

The pre-trained language models, e.g., ELMo and BERT, have recently achieved promising performance improvement in a wide range of NLP tasks, because they can output strong contextualized embedded features of words. Inspired by their great success, in this paper we target at fine-tuning them to effectively handle the text clustering task, i.e., a classic and fundamental challenge in machine learning. Accordingly, we propose a novel BERT-based method, namely Text Clustering with Dual Word-level Augmentation (TCDWA). To be specific, we formulate a self-training objective and enhance it with a dual word-level augmentation technique. First, we suppose that each text contains several most informative words, called anchor words, supporting the full text semantics. We use the embedded features of anchor words as augmented data, which are selected by ranking the norm-based attention weights of words. Second, we formulate an expectation form of word augmentation, which is equivalent to generating infinite augmented features, and further suggest a tractable approximation of Taylor expansion for efficient optimization. To evaluate the effectiveness of TCDWA, we conduct extensive experiments on several benchmark text datasets. The results demonstrate that TCDWA consistently outperforms the state-of-the-art baseline methods. Code available: https://github.com/BoCheng-96/TC-DWA.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Variational Wasserstein Barycenters with C-cyclical Monotonicity Regularization

Jinjin Chi
Zhiyao Yang
Ximing Li
Jihong Ouyang
Renchu Guan

Wasserstein barycenter, built on the theory of Optimal Transport (OT), provides a powerful framework to aggregate probability distributions, and it has increasingly attracted great attention within the machine learning community. However, it is often intractable to precisely compute, especially for high dimensional and continuous settings. To alleviate this problem, we develop a novel regularization by using the fact that c-cyclical monotonicity is often necessary and sufficient conditions for optimality in OT problems, and incorporate it into the dual formulation of Wasserstein barycenters. For efficient computations, we adopt a variational distribution as the approximation of the true continuous barycenter, so as to frame the Wasserstein barycenters problem as an optimization problem with respect to variational parameters. Upon those ideas, we propose a novel end-to-end continuous approximation method, namely Variational Wasserstein Barycenters with c-Cyclical Monotonicity Regularization (VWB-CMR), given sample access to the input distributions. We show theoretical convergence analysis and demonstrate the superior performance of VWB-CMR on synthetic data and real applications of subset posterior aggregation.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

Weakly-supervised Text Classification with Wasserstein Barycenters Regularization

Jihong Ouyang
Yiming Wang
Ximing Li
Changchun Li

Weakly-supervised text classification aims to train predictive models with unlabeled texts and a few representative words of classes, referred to as category words, rather than labeled texts. These weak supervisions are much more cheaper and easy to collect in real-world scenarios. To resolve this task, we propose a novel deep classification model, namely Weakly-supervised Text Classification with Wasserstein Barycenter Regularization (WTC-WBR). Specifically, we initialize the pseudo-labels of texts by using the category word occurrences, and formulate a weakly self-training framework to iteratively update the weakly-supervised targets by combining the pseudo-labels with the sharpened predictions. Most importantly, we suggest a Wasserstein barycenter regularization with the weakly-supervised targets on the deep feature space. The intuition is that the texts tend to be close to the corresponding Wasserstein barycenter indicated by weakly-supervised targets. Another benefit is that the regularization can capture the geometric information of deep feature space to boost the discriminative power of deep features. Experimental results demonstrate that WTC-WBR outperforms the existing weakly-supervised baselines, and achieves comparable performance to semi-supervised and supervised baselines.

PDF Details DOI

IJCAI Conference 2021 Conference Paper

Layer-Assisted Neural Topic Modeling over Document Networks

Yiming Wang
Ximing Li
Jihong Ouyang

Neural topic modeling provides a flexible, efficient, and powerful way to extract topic representations from text documents. Unfortunately, most existing models cannot handle the text data with network links, such as web pages with hyperlinks and scientific papers with citations. To resolve this kind of data, we develop a novel neural topic model, namely Layer-Assisted Neural Topic Model (LANTM), which can be interpreted from the perspective of variational auto-encoders. Our major motivation is to enhance the topic representation encoding by not only using text contents, but also the assisted network links. Specifically, LANTM encodes the texts and network links to the topic representations by an augmented network with graph convolutional modules, and decodes them by maximizing the likelihood of the generative process. The neural variational inference is adopted for efficient inference. Experimental results validate that LANTM significantly outperforms the existing models on topic quality, text classification and link prediction. .

PDF Details DOI

IJCAI Conference 2020 Conference Paper

Recovering Accurate Labeling Information from Partially Valid Data for Effective Multi-Label Learning

Ximing Li
Yang Wang

Partial Multi-label Learning (PML) aims to induce the multi-label predictor from datasets with noisy supervision, where each training instance is associated with several candidate labels but only partially valid. To address the noisy issue, the existing PML methods basically recover the ground-truth labels by leveraging the ground-truth confidence of the candidate label, i. e. , the likelihood of a candidate label being a ground-truth one. However, they neglect the information from non-candidate labels, which potentially contributes to the ground-truth label recovery. In this paper, we propose to recover the ground-truth labels, i. e. , estimating the ground-truth confidences, from the label enrichment, composed of the relevance degrees of candidate labels and irrelevance degrees of non-candidate labels. Upon this observation, we further develop a novel two-stage PML method, namely Partial Multi-Label Learning with Label Enrichment-Recovery (PML3ER), where in the first stage, it estimates the label enrichment with unconstrained label propagation, then jointly learns the ground-truth confidence and multi-label predictor given the label enrichment. Experimental results validate that PML3ER outperforms the state-of-the-art PML methods.

PDF Details DOI

AAAI Conference 2020 Conference Paper

Reduction and Local Search for Weighted Graph Coloring Problem

Yiyuan Wang
Shaowei Cai
Shiwei Pan
Ximing Li
Monghao Yin

The weighted graph coloring problem (WGCP) is an important extension of the graph coloring problem (GCP) with wide applications. Compared to GCP, where numerous methods have been developed and even massive graphs with millions of vertices can be solved well, fewer works have been done for WGCP, and no solution is available for solving WGCP for massive graphs. This paper explores techniques for solving WGCP, including a lower bound and a reduction rule based on clique sampling, and a local search algorithm based on two selection rules and a new variant of conﬁguration checking. This results in our algorithm RedLS (Reduction plus Local Search). Experiments are conducted to compare RedLS with the state-of-the-art algorithms on massive graphs as well as conventional benchmarks studied in previous works. RedLS exhibits very good performance and robustness. It signiﬁcantly outperforms previous algorithms on all benchmarks.

PDF Details

TCS Journal 2019 Journal Article

Accumulating automata and cascaded equations automata for communicationless information theoretically secure multi-party computation

Shlomi Dolev
Niv Gilboa
Ximing Li

Information theoretically secure multi-party computation implies severe communication overhead among the computing participants, as there is a need to reduce the polynomial degree after each multiplication. In particular, when the input is (practically) unbounded, the number of multiplications and therefore the communication bandwidth among the participants may be practically unbounded. In some scenarios the communication among the participants should better be avoided altogether, avoiding linkage among the secret share holders. For example, when processes in clouds operate over streaming secret shares without communicating with each other, they can actually hide their linkage and activity in the crowd. An adversary that is able to compromise processes in the cloud may need to capture and analyze a very large number of possible shares. Consider a dealer that wants to repeatedly compute functions on a long file with the assistance of m servers. The dealer does not wish to leak either the input file or the result of the computation to any of the servers. We investigate this setting given two constraints. The dealer is allowed to share each symbol of the input file among the servers and is allowed to halt the computation at any point. However, the dealer is otherwise stateless. Furthermore, each server is not allowed any communication beyond the shares of the inputs that it receives and the information it provides to the dealer during reconstruction. We present a protocol in this setting for generalized string matching, including wildcards. We also present solutions for identifying other regular languages, as well as particular context free and context sensitive languages. The results can be described by a newly defined accumulating automata (AA) and cascaded equations automata (CEA) which may be of an independent interest. As an application of accumulating automata and cascaded equations automata, secure and private repeated computations on a secret shared file among communicationless clouds are presented.

Details DOI

IJCAI Conference 2019 Conference Paper

Approximate Optimal Transport for Continuous Densities with Copulas

Jinjin Chi
Jihong Ouyang
Ximing Li
Yang Wang
Meng Wang

Optimal Transport (OT) formulates a powerful framework by comparing probability distributions, and it has increasingly attracted great attention within the machine learning community. However, it suffers from severe computational burden, due to the intractable objective with respect to the distributions of interest. Especially, there still exist very few attempts for continuous OT, i. e. , OT for comparing continuous densities. To this end, we develop a novel continuous OT method, namely Copula OT (Cop-OT). The basic idea is to transform the primal objective of continuous OT into a tractable form with respect to the copula parameter, which can be efficiently solved by stochastic optimization with less time and memory requirements. Empirical results on real applications of image retrieval and synthetic data demonstrate that our Cop-OT can gain more accurate approximations to continuous OT values than the state-of-the-art baselines.

PDF Details

AAAI Conference 2019 Conference Paper

Dirichlet Multinomial Mixture with Variational Manifold Regularization: Topic Modeling over Short Texts

Ximing Li
Jiaojiao Zhang
Jihong Ouyang

Conventional topic models suffer from a severe sparsity problem when facing extremely short texts such as social media posts. The family of Dirichlet multinomial mixture (DMM) can handle the sparsity problem, however, they are still very sensitive to ordinary and noisy words, resulting in inaccurate topic representations at the document level. In this paper, we alleviate this problem by preserving local neighborhood structure of short texts, enabling to spread topical signals among neighboring documents, so as to correct the inaccurate topic representations. This is achieved by using variational manifold regularization, constraining the close short texts should have similar variational topic representations. Upon this idea, we propose a novel Laplacian DMM (LapDMM) topic model. During the document graph construction, we further use the word mover’s distance with word embeddings to measure document similarities at the semantic level. To evaluate LapDMM, we compare it against the state-of-theart short text topic models on several traditional tasks. Experimental results demonstrate that our LapDMM achieves very significant performance gains over baseline models, e. g. , achieving even about 0. 2 higher scores on clustering and classification tasks in many cases.

PDF Details

IJCAI Conference 2018 Conference Paper

Variance Reduction in Black-box Variational Inference by Adaptive Importance Sampling

Ximing Li
Changchun Li
Jinjin Chi
Jihong Ouyang

Overdispersed black-box variational inference employs importance sampling to reduce the variance of the Monte Carlo gradient in black-box variational inference. A simple overdispersed proposal distribution is used. This paper aims to investigate how to adaptively obtain better proposal distribution for lower variance. To this end, we directly approximate the optimal proposal in theory using a Monte Carlo moment matching step at each variational iteration. We call this adaptive proposal moment matching proposal (MMP). Experimental results on two Bayesian models show that the MMP can effectively reduce variance in black-box learning, and perform better than baseline inference algorithms.

PDF Details

TCS Journal 2016 Journal Article

Magnifying computing gaps

Shlomi Dolev
Ephraim Korach
Ximing Li
Yin Li
Galit Uzan

In the field of information security, the best way of protecting the privacy of the participants is to keep silent. Consider two, not necessarily identical, powerful computers or computer-grids connected by a unidirectional communication link that should transfer a long stream of information in the presence of a listening adversary that is slightly weaker. We present schemes that enhance the computation strength gap between the powerful computers and the adversary. The gap between the amount of information decrypted by the adversary and the information decrypted by the receiver grows with time. Based on a new defined shortest vector problem, we also propose a simplified version scheme in which only the receivers are computationally powerful. The scheme is self-stabilizing in the sense that it can establish a security level without relying on (previously distributed private keys that are part of) the state. The iterative nested approach can be used for enhancing the security of the classical protocol of Ralph Merkle [19]. Several applications for sensor networks and for secure communication with survivors are suggested.

Details DOI