Jing Ma

AAAI Conference 2026 Conference Paper

Breaking the Adversarial Robustness-Performance Trade-off in Text Classification via Manifold Purification

• Chenhao Dang
• Jing Ma

A persistent challenge in text classification (TC) is that enhancing model robustness against adversarial attacks typically degrades performance on clean data. We argue that this challenge can be resolved by modeling the distribution of clean samples in the encoder’s embedding manifold. To this end, we propose the Manifold-Correcting Causal Flow (MC²F), a two-module system that operates directly on sentence embeddings. A Stratified Riemannian Continuous Normalizing Flow (SR-CNF) learns the density of the clean data manifold. It identifies out-of-distribution embeddings, which are then corrected by a Geodesic Purification Solver. This solver projects adversarial points back onto the learned manifold via the shortest path, restoring a clean, semantically coherent representation. We conducted extensive evaluations on text classification (TC) across three datasets and multiple adversarial attacks. The results demonstrate that our method, MC²F, not only establishes a new state-of-the-art in adversarial robustness but also fully preserves performance on clean data, even yielding modest gains in Accuracy.

AAAI Conference 2026 Conference Paper

Class-Aware Active Annotation in Federated Semi-Supervised Learning for Medical Image Classification

• Meiting Xue
• Miaoqi Li
• Yukun Shi
• Yan Zeng
• Jilin Zhang
• Jing Ma

In medical image classification, data privacy constraints and the high cost of expert annotations pose significant challenges to building generalizable models. Federated semi-supervised learning (FSSL), which combines the privacy-preserving nature of federated learning with the label efficiency of semi-supervised learning, offers a promising direction. However, in real-world deployments, client data often exhibits highly non-independent and identically distributed (Non-IID) characteristics. This distributional heterogeneity undermines the reliability of pseudo-labels generated by global models, ultimately limiting model generalization. A key limitation of existing FSSL approaches lies in their reliance on a static labeled set fixed prior to training. Such strategies lack the ability to adaptively correct pseudo-label noise or address class imbalance throughout training, particularly under Non-IID settings. To address this, we propose FSSAL, a novel framework that introduces an active learning component into the FSSL pipeline. By continuously identifying informative and representative samples during training, our method adaptively refines the labeled set and enhances the model’s robustness to distribution shifts. FSSAL employs client-private models for pseudo-label generation to reduce global bias, applies a class-aware dynamic thresholding mechanism to ensure more reliable and balanced label selection, and incorporates a sample selection strategy guided by both feature diversity and model uncertainty. Extensive experiments on four public medical image classification datasets demonstrate that FSSAL consistently outperforms competitive FSSL methods in accuracy and F1-score, especially under highly Non-IID conditions, highlighting its robustness and practical potential.

AAAI Conference 2026 Conference Paper

CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Models

• Yuefei Chen
• Vivek K. Singh
• Jing Ma
• Ruixiang Tang

Counterfactual reasoning is widely recognized as one of the most challenging and intricate aspects of causality in artificial intelligence. In this paper, we evaluate the performance of large language models (LLMs) in counterfactual reasoning. In contrast to previous studies that primarily focus on commonsense causal reasoning, where LLMs often rely on prior knowledge for inference, we specifically assess their ability to perform counterfactual inference using a set of formal rules. To support this evaluation, we introduce a new benchmark dataset, CounterBench, comprising 1.2K counterfactual reasoning questions. The dataset is designed with varying levels of difficulty, diverse causal graph structures, distinct types of counterfactual questions, and multiple nonsensical name variants. Our experiments demonstrate that counterfactual reasoning poses a significant challenge for LLMs, with most models performing at levels comparable to random guessing. To enhance LLM's counterfactual reasoning ability, we propose a novel reasoning paradigm, CoIn, which guides LLMs through iterative reasoning and backtracking to systematically explore counterfactual solutions. Experimental results show that our method significantly improves LLM performance on counterfactual reasoning tasks and consistently enhances performance across different LLMs.

TIST Journal 2026 Journal Article

GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse

• Hongzhan Lin
• Ziyang Luo
• Bo Wang
• Ruichao Yang
• Jing Ma

The exponential growth of social media has profoundly transformed how information is created, disseminated, and absorbed, exceeding any precedent in the digital age. Regrettably, this explosion has also spawned a significant increase in the online abuse of memes. Evaluating the negative impact of memes is notably challenging, owing to their often subtle and implicit meanings, which are not directly conveyed through the overt text and image. In light of this, Large Multimodal Models (LMMs) have emerged as a focal point of interest due to their remarkable capabilities in handling diverse multimodal tasks. In response to this development, our article aims to thoroughly examine the capacity of various LMMs (e.g., GPT-4V, LLaVA, and Qwen-VL) to discern and respond to the nuanced aspects of social abuse manifested in memes. We introduce the comprehensive meme benchmark, GOAT-Bench, comprising over 6K varied memes encapsulating themes, such as implicit hate speech, sexism, and cyberbullying. Utilizing GOAT-Bench, we delve into the ability of LMMs to accurately assess hatefulness, misogyny, offensiveness, sarcasm, and harmful content. Our extensive experiments across a range of LMMs reveal that current models still exhibit a deficiency in safety awareness, showing insensitivity to various forms of implicit abuse. We posit that this shortfall represents a critical impediment to the realization of safe artificial intelligence. The GOAT-Bench and accompanying resources are publicly accessible at https://goatlmm.github.io/, contributing to ongoing research in this vital field.

AAAI Conference 2025 Conference Paper

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models

• Peihai Jiang
• Xixiang Lyu
• Yige Li
• Jing Ma

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of malicious samples can successfully embed backdoor triggers into the model. While most existing defense methods focus on post-training backdoor defense, efficiently defending against backdoor attacks during training phase remains largely unexplored. To address this gap, we propose a novel defense method called Backdoor Token Unlearning (BTU), which proactively detects and neutralizes trigger tokens during the training stage. Our work is based on two key findings: 1) backdoor learning causes distinctive differences between backdoor token parameters and clean token parameters in word embedding layers, and 2) the success of backdoor attacks heavily depends on backdoor token parameters. The BTU defense leverages these properties to identify aberrant embedding parameters and subsequently removes backdoor behaviors using a fine-grained unlearning technique. Extensive evaluations across three datasets and four types of backdoor attacks demonstrate that BTU effectively defends against these threats while preserving the model’s performance on primary tasks.

AAAI Conference 2025 Conference Paper

Certified Causal Defense with Generalizable Robustness

• Yiran Qiao
• Yu Yin
• Chen Chen
• Jing Ma

While machine learning models have proven effective across various scenarios, it is widely acknowledged that many models are vulnerable to adversarial attacks. Recently, numerous efforts have emerged in adversarial defense. Among them, certified defense is well known for its theoretical guarantees against arbitrary adversarial perturbations on input within a certain range. However, most existing works in this line struggle to generalize their certified robustness in other data domains with distribution shifts. This issue is rooted in the difficulty of eliminating the negative impact of spurious correlations on robustness in different domains. To address this problem, in this work, we propose a novel certified defense framework GLEAN, which incorporates a causal perspective into the generalization problem in certified defense. More specifically, our framework integrates a certifiable causal factor learning component to disentangle the causal relations and spurious correlations between input and label, thereby excluding the negative effect of spurious correlations on defense. On top of that, we design a causally certified defense strategy to handle adversarial attacks on latent causal factors. In this way, our framework is not only robust against malicious noises on data in the training distribution but also can generalize its robustness across domains with distribution shifts. Extensive experiments on benchmark datasets validate the superiority of our framework in certified robustness generalization in different data domains.

NeurIPS Conference 2025 Conference Paper

Decoupled Entropy Minimization

• Jing Ma
• Hanlin Li
• Xiang Xiang

Entropy Minimization (EM) is beneficial to reducing class overlap, bridging domain gap, and restricting uncertainty for various tasks in machine learning, yet its potential is limited. To study the internal mechanism of EM, we reformulate and decouple the classical EM into two parts with opposite effects: cluster aggregation driving factor (CADF) rewards dominant classes and prompts a peaked output distribution, while gradient mitigation calibrator (GMC) penalizes high-confidence classes based on predicted probabilities. Furthermore, we reveal the limitations of classical EM caused by its coupled formulation: 1) reward collapse impedes the contribution of high-certainty samples in the learning process, and 2) easy-class bias induces misalignment between output distribution and label distribution. To address these issues, we propose Adaptive Decoupled Entropy Minimization (AdaDEM), which normalizes the reward brought from CADF and employs a marginal entropy calibrator (MEC) to replace GMC. AdaDEM outperforms DEM*, an upper-bound variant of classical EM, and achieves superior performance across various imperfectly supervised learning tasks in noisy and dynamic environments.

TMLR Journal 2025 Journal Article

Global Graph Counterfactual Explanation: A Subgraph Mapping Approach

• Yinhan He
• Wendy Zheng
• Yaochen Zhu
• Jing Ma
• Saumitra Mishra
• Natraj Raman
• Ninghao Liu
• Jundong Li

Graph Neural Networks (GNNs) have been widely deployed in various real-world applications. However, most GNNs are black-box models that lack explanations. One strategy to explain GNNs is through counterfactual explanation, which aims to find minimum perturbations on input graphs that change the GNN predictions. Existing works on GNN counterfactual explanations primarily concentrate on the local-level perspective (i.e., generating counterfactuals for each individual graph), which suffers from information overload and lacks insights into the broader cross-graph relationships. To address such issues, we propose GlobalGCE, a novel global-level graph counterfactual explanation method. GlobalGCE aims to identify a collection of subgraph mapping rules as counterfactual explanations for the target GNN. According to these rules, substituting certain significant subgraphs with their counterfactual subgraphs will change the GNN prediction to the desired class for most graphs (i.e., maximum coverage). Methodologically, we design a significant subgraph generator and a counterfactual subgraph autoencoder in our GlobalGCE, where the subgraphs and the rules can be effectively generated. Extensive experiments demonstrate the superiority of our GlobalGCE compared to existing baselines. Our code can be found at \url{https://github.com/YinhanHe123/GlobalGCE}.

TIST Journal 2025 Journal Article

LLM-enhanced Multiple Instance Learning for Joint Rumor and Stance Detection with Social Context Information

• Ruichao Yang
• Jing Ma
• Wei Gao
• Hongzhan Lin

The proliferation of misinformation, such as rumors on social media, has drawn significant attention, prompting various expressions of stance among users. Although rumor detection and stance detection are distinct tasks, they can complement each other. Rumors can be identified by cross-referencing stances in related posts, and stances are influenced by the nature of the rumor. However, existing stance detection methods often require post-level stance annotations, which are costly to obtain. We propose a novel LLM-enhanced MIL approach to jointly predict post stance and claim class labels, supervised solely by claim labels, using an undirected microblog propagation model. Our weakly supervised approach relies only on bag-level labels of claim veracity, aligning with multi-instance learning (MIL) principles. To achieve this, we transform the multi-class problem into multiple MIL-based binary classification problems. We then employ a discriminative attention layer to aggregate the outputs from these classifiers into finer-grained classes. Experiments conducted on three rumor datasets and two stance datasets demonstrate the effectiveness of our approach, highlighting strong connections between rumor veracity and expressed stances in responding posts. Our method shows promising performance in joint rumor and stance detection compared to the state-of-the-art methods.

JBHI Journal 2025 Journal Article

MCD-LightGBM System for Intelligent Analyzing Heterogeneous Clinical Drug Therapeutic Effects

• Xiao-Hui Yang
• Hao-Jie Liao
• Pei-Yu Sun
• Jing Ma
• Bing Wang
• Yan He
• Liu-Gen Xue
• Li-Min Su

Causal effect estimation of individual heterogeneity is a core issue in the field of causal inference, and its application in medicine poses an active and challenging problem. In high-risk decision-making domain such as healthcare, inappropriate treatments can have serious negative impacts on patients. Recently, machine learning-based methods have been proposed to improve the accuracy of causal effect estimation results. However, many of these methods concentrate on estimating causal effects of continuous outcome variables under binary intervention conditions, and give less consideration to multivariate intervention conditions or discrete outcome variables, thus limiting their scope of application. To tackle this issue, we combine the double machine learning framework with Light Gradient Boosting Machine (LightGBM) and propose a double LightGBM model. This model can estimate binary causal effects more accurately and in less time. Two cyclic structures were added to the model. Data correction method was introduced and improved to transform discrete outcome variables into continuous outcome variables. Multivariate Cyclic Double LightGBM model (MCD-LightGBM) was proposed to intelligently estimate multivariate treatment effects. A visual human-computer interaction system for heterogeneous causal effect estimation was designed, which can be applied to different types of data. This paper reports that the system improved the Logarithm of the Minimum Angle of Resolution (LogMAR) of visual acuity change after Vascular Endothelial Growth Factor (anti-VEGF) treatment in patients with diabetic macular degeneration. The improvement was observed in two clinical problems, from 0. 05 to 0. 33, and the readmission rate of diabetic patients after cure was reduced from 48. 4% to 10. 5%. The results above demonstrate the potential of the proposed system in predicting heterogeneous clinical drug treatment effects.

AAAI Conference 2025 Conference Paper

Meme Trojan: Backdoor Attacks Against Hateful Meme Detection via Cross-Modal Triggers

• Ruofei Wang
• Hongzhan Lin
• Ziyuan Luo
• Ka Chun Cheung
• Simon See
• Jing Ma
• Renjie Wan

Hateful meme detection aims to prevent the proliferation of hateful memes on various social media platforms. Considering its impact on social environments, this paper introduces a previously ignored but significant threat to hateful meme detection: backdoor attacks. By injecting specific triggers into meme samples, backdoor attackers can manipulate the detector to output their desired outcomes. To explore this, we propose the Meme Trojan framework to initiate backdoor attacks on hateful meme detection. Meme Trojan involves creating a novel Cross-Modal Trigger (CMT) and a learnable trigger augmentor to enhance the trigger pattern according to each input sample. Due to the cross-modal property, the proposed CMT can effectively initiate backdoor attacks on hateful meme detectors under an automatic application scenario. Additionally, the injection position and size of our triggers are adaptive to the texts contained in the meme, which ensures that the trigger is seamlessly integrated with the meme content. Our approach outperforms the state-of-the-art backdoor attack methods, showing significant improvements in effectiveness and stealthiness. We believe that this paper will draw more attention to the potential threat posed by backdoor attacks on hateful meme detection.

ICML Conference 2025 Conference Paper

PTTA: Purifying Malicious Samples for Test-Time Model Adaptation

• Jing Ma
• Hanlin Li
• Xiang Xiang 0001

Test-Time Adaptation (TTA) enables deep neural networks to adapt to arbitrary distributions during inference. Existing TTA algorithms generally tend to select benign samples that help achieve robust online prediction and stable self-training. Although malicious samples that would undermine the model’s optimization should be filtered out, it also leads to a waste of test data. To alleviate this issue, we focus on how to make full use of the malicious test samples for TTA by transforming them into benign ones, and propose a plug-and-play method, PTTA. The core of our solution lies in the purification strategy, which retrieves benign samples having opposite effects on the objective function to perform Mixup with malicious samples, based on a saliency indicator for encoding benign and malicious data. This strategy results in effective utilization of the information in malicious samples and an improvement of the models’ online test accuracy. In this way, we can directly apply the purification loss to existing TTA algorithms without the need to carefully adjust the sample selection threshold. Extensive experiments on four types of TTA tasks as well as classification, segmentation, and adversarial defense demonstrate the effectiveness of our method. Code is available at https: //github. com/HAIV-Lab/PTTA.

NeurIPS Conference 2025 Conference Paper

Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting

• Yiren Lu
• Yunlai Zhou
• Yiran Qiao
• Chaoda Song
• Tuo Liang
• Jing Ma
• Huan Wang
• Yu Yin

Open-vocabulary querying in 3D space is crucial for enabling more intelligent perception in applications such as robotics, autonomous systems, and augmented reality. However, most existing methods rely on 2D pixel-level parsing, leading to multi-view inconsistencies and poor 3D object retrieval. Moreover, they are limited to static scenes and struggle with dynamic scenes due to the complexities of motion modeling. In this paper, we propose Segment then Splat, a 3D-aware open vocabulary segmentation approach for both static and dynamic scenes based on Gaussian Splatting. Segment then Splat reverses the long established approach of "segmentation after reconstruction'' by dividing Gaussians into distinct object sets before reconstruction. Once reconstruction is complete, the scene is naturally segmented into individual objects, achieving true 3D segmentation. This design eliminates both geometric and semantic ambiguities, as well as Gaussian–object misalignment issues in dynamic scenes. It also accelerates the optimization process, as it eliminates the need for learning a separate language field. After optimization, a CLIP embedding is assigned to each object to enable open-vocabulary querying. Extensive experiments on various datasets demonstrate the effectiveness of our proposed method in both static and dynamic scenarios.

TMLR Journal 2024 Journal Article

A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law

• Zhiyu Chen
• Jing Ma
• Xinlu Zhang
• Nan Hao
• An Yan
• Armineh Nourbakhsh
• Xianjun Yang
• Julian McAuley

In the fast-evolving domain of artificial intelligence, large language models (LLMs) such as GPT-3 and GPT-4 are revolutionizing the landscapes of finance, healthcare, and law: domains characterized by their reliance on professional expertise, challenging data acquisition, high-stakes, and stringent regulatory compliance. This survey offers a detailed exploration of the methodologies, applications, challenges, and forward-looking opportunities of LLMs within these high-stakes sectors. We highlight the instrumental role of LLMs in enhancing diagnostic and treatment methodologies in healthcare, innovating financial analytics, and refining legal interpretation and compliance strategies. Moreover, we critically examine the ethics for LLM applications in these fields, pointing out the existing ethical concerns and the need for transparent, fair, and robust AI systems that respect regulatory norms. By presenting a thorough review of current literature and practical applications, we showcase the transformative impact of LLMs, and outline the imperative for interdisciplinary cooperation, methodological advancements, and ethical vigilance. Through this lens, we aim to spark dialogue and inspire future research dedicated to maximizing the benefits of LLMs while mitigating their risks in these precision-dependent sectors. To facilitate future research on LLMs in these critical societal domains, we also initiate a reading list that tracks the latest advancements under this topic, which will be released and continually updated.

NeurIPS Conference 2024 Conference Paper

Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions

• Zhe Hu
• Tuo Liang
• Jing Li
• Yiren Lu
• Yunlai Zhou
• Yiran Qiao
• Jing Ma
• Yu Yin

Recent advancements in large vision language models have demonstrated remarkable proficiency across a wide range of tasks. Yet, these models still struggle with understanding the nuances of human humor through juxtaposition, particularly when it involves nonlinear narratives that underpin many jokes and humor cues. This paper investigates this challenge by focusing on comics with contradictory narratives, where each comic consists of two panels that create a humorous contradiction. We introduce the YesBut benchmark, which comprises tasks of varying difficulty aimed at assessing AI's capabilities in recognizing and interpreting these comics, ranging from literal content comprehension to deep narrative reasoning. Through extensive experimentation and analysis of recent commercial or open-sourced large vision language models, we assess their capability to comprehend the complex interplay of the narrative humor inherent in these comics. Our results show that even the state-of-the-art models still struggle with this task. Our findings offer insights into the current limitations and potential improvements for AI in understanding human creative expressions.

EAAI Journal 2024 Journal Article

Graph attention network with convolutional layer for predicting gene regulations from single-cell ribonucleic acid sequence data

• Junjiang Liu
• Shusen Zhou
• Jing Ma
• Mujun Zang
• Chanjuan Liu
• Tong Liu
• Qingjun Wang

AAAI Conference 2024 Conference Paper

When Causal Inference Meets Graph Machine Learning

• Jing Ma

Graphs (i.e., networks) are ubiquitous in daily life, as they can effectively model a plethora of real-world systems with connected units, such as social networks and biological networks. Recent years have witnessed rapid development in graph-based machine learning (GML) in various high-impact domains. Currently, the mainstream GML methods are based on statistical learning, e.g., utilizing the statistical correlations between node features, graph structure, and labels for node classification. However, statistical learning has been widely criticized for only capturing the superficial relations between variables in the data system, and consequently, rendering the lack of trustworthiness in real-world applications. Therefore, it is crucial to understand the causality in the data system and the learning process. Causal inference is the discipline that investigates the causality inside a system, for example, to identify and estimate the causal effect of a certain treatment (e.g., wearing a face mask) on an important outcome (e.g., COVID-19 infection). Involving the concepts and philosophy of causal inference in ML methods is often considered significant for human-level intelligence and can serve as the foundation of artificial intelligence (AI). However, most traditional causal inference studies rely on strong assumptions, and focus on independent and identically distributed (i.i.d.) data, while causal inference on graphs is faced with many barriers. Therefore, we aim to bridge the gap between causal inference and GML.

AAAI Conference 2023 Conference Paper

Interpreting Unfairness in Graph Neural Networks via Training Node Attribution

• Yushun Dong
• Song Wang
• Jing Ma
• Ninghao Liu
• Jundong Li

Graph Neural Networks (GNNs) have emerged as the leading paradigm for solving graph analytical problems in various real-world applications. Nevertheless, GNNs could potentially render biased predictions towards certain demographic subgroups. Understanding how the bias in predictions arises is critical, as it guides the design of GNN debiasing mechanisms. However, most existing works overwhelmingly focus on GNN debiasing, but fall short on explaining how such bias is induced. In this paper, we study a novel problem of interpreting GNN unfairness through attributing it to the influence of training nodes. Specifically, we propose a novel strategy named Probabilistic Distribution Disparity (PDD) to measure the bias exhibited in GNNs, and develop an algorithm to efficiently estimate the influence of each training node on such bias. We verify the validity of PDD and the effectiveness of influence estimation through experiments on real-world datasets. Finally, we also demonstrate how the proposed framework could be used for debiasing GNNs. Open-source code can be found at https://github.com/yushundong/BIND.

IJCAI Conference 2023 Conference Paper

Learning Causal Effects on Hypergraphs (Extended Abstract)

• Jing Ma
• Mengting Wan
• Longqi Yang
• Jundong Li
• Brent Hecht
• Jaime Teevan

Hypergraphs provide an effective abstraction for modeling multi-way group interactions among nodes, where each hyperedge can connect any number of nodes. Different from most existing studies which leverage statistical dependencies, we study hypergraphs from the perspective of causality. Specifically, we focus on the problem of individual treatment effect (ITE) estimation on hypergraphs, aiming to estimate how much an intervention (e. g. , wearing face covering) would causally affect an outcome (e. g. , COVID-19 infection) of each individual node. Existing works on ITE estimation either assume that the outcome of one individual should not be influenced by the treatment of other individuals (i. e. , no interference), or assume the interference only exists between connected individuals in an ordinary graph. We argue that these assumptions can be unrealistic on real-world hypergraphs, where higher-order interference can affect the ITE estimations due to group interactions. We investigate high-order interference modeling, and propose a new causality learning framework powered by hypergraph neural networks. Extensive experiments on real-world hypergraphs verify the superiority of our framework over existing baselines.

AAAI Conference 2023 Conference Paper

Zero-Shot Rumor Detection with Propagation Structure via Prompt Learning

• Hongzhan Lin
• Pengyao Yi
• Jing Ma
• Haiyun Jiang
• Ziyang Luo
• Shuming Shi
• Ruifang Liu

The spread of rumors along with breaking events seriously hinders the truth in the era of social media. Previous studies reveal that due to the lack of annotated resources, rumors presented in minority languages are hard to be detected. Furthermore, the unforeseen breaking events not involved in yesterday's news exacerbate the scarcity of data resources. In this work, we propose a novel zero-shot framework based on prompt learning to detect rumors falling in different domains or presented in different languages. More specifically, we firstly represent rumor circulated on social media as diverse propagation threads, then design a hierarchical prompt encoding mechanism to learn language-agnostic contextual representations for both prompts and rumor data. To further enhance domain adaptation, we model the domain-invariant structural features from the propagation threads, to incorporate structural position representations of influential community response. In addition, a new virtual response augmentation method is used to improve model training. Extensive experiments conducted on three real-world datasets demonstrate that our proposed model achieves much better performance than state-of-the-art methods and exhibits a superior capacity for detecting rumors at early stages.

NeurIPS Conference 2022 Conference Paper

CLEAR: Generative Counterfactual Explanations on Graphs

• Jing Ma
• Ruocheng Guo
• Saumitra Mishra
• Aidong Zhang
• Jundong Li

Counterfactual explanations promote explainability in machine learning models by answering the question “how should the input instance be altered to obtain a desired predicted label? ". The comparison of this instance before and after perturbation can enhance human interpretation. Most existing studies on counterfactual explanations are limited in tabular data or image data. In this paper, we study the problem of counterfactual explanation generation on graphs. A few studies have explored to generate counterfactual explanations on graphs, but many challenges of this problem are still not well-addressed: 1) optimizing in the discrete and disorganized space of graphs; 2) generalizing on unseen graphs; 3) maintaining the causality in the generated counterfactuals without prior knowledge of the causal model. To tackle these challenges, we propose a novel framework CLEAR which aims to generate counterfactual explanations on graphs for graph-level prediction models. Specifically, CLEAR leverages a graph variational autoencoder based mechanism to facilitate its optimization and generalization, and promotes causality by leveraging an auxiliary variable to better identify the causal model. Extensive experiments on both synthetic and real-world graphs validate the superiority of CLEAR over state-of-the-art counterfactual explanation methods on graphs in different aspects.

JBHI Journal 2021 Journal Article

Estimating Time to Progression of Chronic Obstructive Pulmonary Disease With Tolerance

• Chunlei Tang
• Joseph M. Plasek
• Xiao Shi
• Meihan Wan
• Haohan Zhang
• Min-Jeoung Kang
• Liqin Wang
• Sevan M. Dulgarian

We defined tolerance range as the distance of observing similar disease conditions or functional status from the upper to the lower boundaries of a specified time interval. A tolerance range was identified for linear regression and support vector machines to optimize the improvement rate (defined as IR) on accuracy in predicting mortality risk in patients with chronic obstructive pulmonary disease using clinical notes. The corpus includes pulmonary, cardiology, and radiology reports of 15, 500 patients who died between 2011 and 2017. Their performance was compared against a long short-term memory recurrent neural network. The results demonstrate an overall improvement by those basic machine learning approaches after considering an optimal tolerance range: the average IR of linear regression was 90. 1% and the maximum IR of support vector machines was 66. 2%. There was a similitude between the time segments produced by our tolerance algorithms and those produced by the long short-term memory.

NeurIPS Conference 2021 Conference Paper

Federated Graph Classification over Non-IID Graphs

• Han Xie
• Jing Ma
• Li Xiong
• Carl Yang

Federated learning has emerged as an important paradigm for training machine learning models in different domains. For graph-level tasks such as graph classification, graphs can also be regarded as a special type of data samples, which can be collected and stored in separate local systems. Similar to other domains, multiple local systems, each holding a small set of graphs, may benefit from collaboratively training a powerful graph mining model, such as the popular graph neural networks (GNNs). To provide more motivation towards such endeavors, we analyze real-world graphs from different domains to confirm that they indeed share certain graph properties that are statistically significant compared with random graphs. However, we also find that different sets of graphs, even from the same domain or same dataset, are non-IID regarding both graph structures and node features. To handle this, we propose a graph clustered federated learning (GCFL) framework that dynamically finds clusters of local systems based on the gradients of GNNs, and theoretically justify that such clusters can reduce the structure and feature heterogeneity among graphs owned by the local systems. Moreover, we observe the gradients of GNNs to be rather fluctuating in GCFL which impedes high-quality clustering, and design a gradient sequence-based clustering mechanism based on dynamic time warping (GCFL+). Extensive experimental results and in-depth analysis demonstrate the effectiveness of our proposed frameworks.

AAAI Conference 2021 Conference Paper

Learning from Crowds by Modeling Common Confusions

• Zhendong Chu
• Jing Ma
• Hongning Wang

Crowdsourcing provides a practical way to obtain large amounts of labeled data at a low cost. However, the annotation quality of annotators varies considerably, which imposes new challenges in learning a high-quality model from the crowdsourced annotations. In this work, we provide a new perspective to decompose annotation noise into common noise and individual noise and differentiate the source of confusion based on instance difficulty and annotator expertise on a per-instance-annotator basis. We realize this new crowdsourcing model by an end-to-end learning solution with two types of noise adaptation layers: one is shared across annotators to capture their commonly shared confusions, and the other one is pertaining to each annotator to realize individual confusion. To recognize the source of noise in each annotation, we use an auxiliary network to choose from the two noise adaptation layers with respect to both instances and annotators. Extensive experiments on both synthesized and real-world benchmarks demonstrate the effectiveness of our proposed common noise adaptation solution.

IJCAI Conference 2021 Conference Paper

Multi-Cause Effect Estimation with Disentangled Confounder Representation

• Jing Ma
• Ruocheng Guo
• Aidong Zhang
• Jundong Li

One fundamental problem in causality learning is to estimate the causal effects of one or multiple treatments (e. g. , medicines in the prescription) on an important outcome (e. g. , cure of a disease). One major challenge of causal effect estimation is the existence of unobserved confounders -- the unobserved variables that affect both the treatments and the outcome. Recent studies have shown that by modeling how instances are assigned with different treatments together, the patterns of unobserved confounders can be captured through their learned latent representations. However, the interpretability of the representations in these works is limited. In this paper, we focus on the multi-cause effect estimation problem from a new perspective by learning disentangled representations of confounders. The disentangled representations not only facilitate the treatment effect estimation but also strengthen the understanding of causality learning process. Experimental results on both synthetic and real-world datasets show the superiority of our proposed framework from different aspects.

IJCAI Conference 2021 Conference Paper

Private Stochastic Non-convex Optimization with Improved Utility Rates

• Qiuchen Zhang
• Jing Ma
• Jian Lou
• Li Xiong

We study the differentially private (DP) stochastic nonconvex optimization with a focus on its under-studied utility measures in terms of the expected excess empirical and population risks. While the excess risks are extensively studied for convex optimization, they are rarely studied for nonconvex optimization, especially the expected population risk. For the convex case, recent studies show that it is possible for private optimization to achieve the same order of excess population risk as to the nonprivate optimization under certain conditions. It still remains an open question for the nonconvex case whether such ideal excess population risk is achievable. In this paper, we progress towards an affirmative answer to this open problem: DP nonconvex optimization is indeed capable of achieving the same excess population risk as to the nonprivate algorithm in most common parameter regimes, under certain conditions (i. e. , well-conditioned nonconvexity). We achieve such improved utility rates compared to existing results by designing and analyzing the stagewise DP-SGD with early momentum algorithm. We obtain both excess empirical risk and excess population risk to achieve differential privacy. Our algorithm also features the first known results of excess and population risks for DP-SGD with momentum. Experiment results on both shallow and deep neural networks when respectively applied to simple and complex real datasets corroborate the theoretical results.

TIST Journal 2020 Journal Article

An Attention-based Rumor Detection Model with Tree-structured Recursive Neural Networks

• Jing Ma
• Wei Gao
• Shafiq Joty
• Kam-Fai Wong

Rumor spread in social media severely jeopardizes the credibility of online content. Thus, automatic debunking of rumors is of great importance to keep social media a healthy environment. While facing a dubious claim, people often dispute its truthfulness sporadically in their posts containing various cues, which can form useful evidence with long-distance dependencies. In this work, we propose to learn discriminative features from microblog posts by following their non-sequential propagation structure and generate more powerful representations for identifying rumors. For modeling non-sequential structure, we first represent the diffusion of microblog posts with propagation trees, which provide valuable clues on how a claim in the original post is transmitted and developed over time. We then present a bottom-up and a top-down tree-structured models based on Recursive Neural Networks (RvNN) for rumor representation learning and classification, which naturally conform to the message propagation process in microblogs. To enhance the rumor representation learning, we reveal that effective rumor detection is highly related to finding evidential posts, e.g., the posts expressing specific attitude towards the veracity of a claim, as an extension of the previous RvNN-based detection models that treat every post equally. For this reason, we design discriminative attention mechanisms for the RvNN-based models to selectively attend on the subset of evidential posts during the bottom-up/top-down recursive composition. Experimental results on four datasets collected from real-world microblog platforms confirm that (1) our RvNN-based models achieve much better rumor detection and classification performance than state-of-the-art approaches; (2) the attention mechanisms for focusing on evidential posts can further improve the performance of our RvNN-based method; and (3) our approach possesses superior capacity on detecting rumors at a very early stage.

IJCAI Conference 2020 Conference Paper

Attention-based Multi-level Feature Fusion for Named Entity Recognition

• Zhiwei Yang
• Hechang Chen
• Jiawei Zhang
• Jing Ma
• Yi Chang

Named entity recognition (NER) is a fundamental task in the natural language processing (NLP) area. Recently, representation learning methods (e. g. , character embedding and word embedding) have achieved promising recognition results. However, existing models only consider partial features derived from words or characters while failing to integrate semantic and syntactic information (e. g. , capitalization, inter-word relations, keywords, lexical phrases, etc. ) from multi-level perspectives. Intuitively, multi-level features can be helpful when recognizing named entities from complex sentences. In this study, we propose a novel framework called attention-based multi-level feature fusion (AMFF), which is used to capture the multi-level features from different perspectives to improve NER. Our model consists of four components to respectively capture the local character-level, global character-level, local word-level, and global word-level features, which are then fed into a BiLSTM-CRF network for the final sequence labeling. Extensive experimental results on four benchmark datasets show that our proposed model outperforms a set of state-of-the-art baselines.

AAMAS Conference 2018 Conference Paper

Incorporating Chorus Line Effect into a Cucker-Smale System for Fast Manoeuvre Tracking

• Jing Ma
• Edmund M-K Lai

IJCAI Conference 2016 Conference Paper

Detecting Rumors from Microblogs with Recurrent Neural Networks

• Jing Ma
• Wei Gao
• Prasenjit Mitra
• Sejeong Kwon
• Bernard J. Jansen
• Kam-Fai Wong
• Meeyoung Cha

Microblogging platforms are an ideal place for spreading rumors and automatically debunking rumors is a crucial problem. To detect rumors, existing approaches have relied on hand-crafted features for employing machine learning algorithms that require daunting manual effort. Upon facing a dubious claim, people dispute its truthfulness by posting various cues over time, which generates long-distance dependencies of evidence. This paper presents a novel method that learns continuous representations of microblog events for identifying rumors. The proposed model is based on recurrent neural networks (RNN) for learning the hidden representations that capture the variation of contextual information of relevant posts over time. Experimental results on datasets from two real-world microblog platforms demonstrate that (1) the RNN method outperforms state-of-the-art rumor detection models that use hand-crafted features; (2) performance of the RNN-based algorithm is further improved via sophisticated recurrent units and extra hidden layers; (3) RNN-based method detects rumors more quickly and accurately than existing techniques, including the leading online rumor debunking services.

JMLR Journal 2016 Journal Article

Joint Structural Estimation of Multiple Graphical Models

• Jing Ma
• George Michailidis

Gaussian graphical models capture dependence relationships between random variables through the pattern of nonzero elements in the corresponding inverse covariance matrices. To date, there has been a large body of literature on both computational methods and analytical results on the estimation of a single graphical model. However, in many application domains, one has to estimate several related graphical models, a problem that has also received attention in the literature. The available approaches usually assume that all graphical models are globally related. On the other hand, in many settings different relationships between subsets of the node sets exist between different graphical models. We develop methodology that jointly estimates multiple Gaussian graphical models, assuming that there exists prior information on how they are structurally related. For many applications, such information is available from external data sources. The proposed method consists of first applying neighborhood selection with a group lasso penalty to obtain edge sets of the graphs, and a maximum likelihood refit for estimating the nonzero entries in the inverse covariance matrices. We establish consistency of the proposed method for sparse high-dimensional Gaussian graphical models and examine its performance using simulation experiments. Applications to a climate data set and a breast cancer data set are also discussed. [abs] [ pdf ][ bib ] &copy JMLR 2016. ( edit, beta )