Author name cluster

Zhong 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.

10 papers

2 author rows

AAAI Conference 2026 Conference Paper

Learning Subgroups with Maximum Treatment Effects Without Causal Heuristics

Lincen Yang
Zhong Li
Matthijs van Leeuwen
Saber Salehkaleybar

Discovering subgroups with the maximum average treatment effect is crucial for targeted decision making in domains such as precision medicine, public policy, and education. While most prior work is formulated in the potential‑outcome framework, the corresponding structural causal model (SCM) for this task has been largely overlooked. In practice, two approaches dominate. The first estimates pointwise conditional treatment effects and then fits a tree on those estimates, effectively turning subgroup estimation into the harder problem of accurate pointwise estimation. The second constructs decision trees or rule sets with ad‑hoc 'causal' heuristics, typically without rigorous justification for why a given heuristic may be used or whether such heuristics are necessary at all. We address these issues by studying the problem directly under the SCM framework. Under the assumption of a partition-based model, we show that optimal subgroup discovery reduces to recovering the data-generating models and hence a standard supervised learning problem (regression or classification). This allows us to adopt any partition-based methods to learn the subgroup from data. We instantiate the approach with CART, arguably one of the most widely used tree-based method, to learn the subgroup with maximum treatment effect. Finally, on a large collection of synthetic and semi‑synthetic datasets, we compare our method against a wide range of baselines and find that our approach, which avoids such causal heuristics, more accurately identifies subgroups with maximum treatment effect.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Towards Automated Self-Supervised Learning for Truly Unsupervised Graph Anomaly Detection (Abstract Reprint)

Zhong Li
Yuhang Wang
Matthijs van Leeuwen

Self-supervised learning (SSL) is an emerging paradigm that exploits supervisory signals generated from the data itself, and many recent studies have leveraged SSL to conduct graph anomaly detection. However, we empirically found that three important factors can substantially impact detection performance across datasets: (1) the specific SSL strategy employed; (2) the tuning of the strategy’s hyperparameters; and (3) the allocation of combination weights when using multiple strategies. Most SSL-based graph anomaly detection methods circumvent these issues by arbitrarily or selectively (i.e., guided by label information) choosing SSL strategies, hyperparameter settings, and combination weights. While an arbitrary choice may lead to subpar performance, using label information in an unsupervised setting is label information leakage and leads to severe overestimation of a method’s performance. Leakage has been criticized as 'one of the top ten data mining mistakes', yet many recent studies on SSL-based graph anomaly detection have been using label information to select hyperparameters. To mitigate this issue, we propose to use an internal evaluation strategy (with theoretical analysis) to select hyperparameters in SSL for unsupervised anomaly detection. We perform extensive experiments using 10 recent SSL-based graph anomaly detection algorithms on various benchmark datasets, demonstrating both the prior issues with hyperparameter selection and the effectiveness of our proposed strategy.

PDF Details DOI

JBHI Journal 2025 Journal Article

NFFGRAM: Nonlinear Multi-Feature Fusion and Gated Recurrent Self-Attention Mechanism for Traditional Chinese Medicine Formula Recommendation

Hailong Hu
Yaqian Li
Zhong Li

Traditional Chinese Medicine (TCM) prescriptions are derived from the distinctive thought process and clinical experiences of Chinese medical theory. With the advent of artificial intelligence (AI), there is an enhanced ability to formulate these prescriptions by analyzing symptom data. However, the inherent sparseness of herb-symptom association data still limits the efficacy of such predictive methods. This study introduces an enhanced bipartite graph diffusion algorithm coupled with a gated recurrent self-attention mechanism for predicting herb and symptom associations. The initial phase involves the reconstruction of the herb-symptom association matrix, leveraging the fractal-weighted K-nearest neighbor algorithm. Subsequently, a method is conceived to extract analogous features between herbs and symptoms, which integrates linear neighborhood similarity with Gaussian kernel similarity, both based on fractal dimensions. The next stage employs a modified bipartite graph diffusion to deduce underlying herb-symptom relationships. This process culminates with the integration of the gated recurrent self-attention mechanism and a confidence scoring system to refine the herb-symptom association predictive matrix at a granular level. We benchmark our results against leading-edge algorithms to ascertain the precision and reliability of our model. Such as improvements of precision@20 by 21. 77%, recall@20 by 12. 46%, and F1-score@20 by 19. 28% compared with the best baseline for the TCM2 dataset. Additionally, comprehensive case studies are undertaken, evaluating recommended prescriptions using insights from contemporary medicine and network pharmacology. The proposed model provides a novel paradigm for enhancing herbal prescription methodologies and TCM herb-based treatments.

Details DOI

NeurIPS Conference 2025 Conference Paper

Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching

Zhong Li
Qi Huang
Yuxuan Zhu
Lincen Yang
Mohammad Mohammadi Amiri
Niki van Stein
Matthijs van Leeuwen

We introduce Time-Conditioned Contraction Matching (TCCM), a novel method for semi-supervised anomaly detection in tabular data. TCCM is inspired by flow matching, a recent generative modeling framework that learns velocity fields between probability distributions and has shown strong performance compared to diffusion models and generative adversarial networks. Instead of directly applying flow matching as originally formulated, TCCM builds on its core idea—learning velocity fields between distributions—but simplifies the framework by predicting a time-conditioned contraction vector toward a fixed target (the origin) at each sampled time step. This design offers three key advantages: (1) a lightweight and scalable training objective that removes the need for solving ordinary differential equations during training and inference; (2) an efficient scoring strategy called one time-step deviation, which quantifies deviation from expected contraction behavior in a single forward pass, addressing the inference bottleneck of existing continuous-time models such as DTE (a diffusion-based model with leading anomaly detection accuracy but heavy inference cost); and (3) explainability and provable robustness, as the learned velocity field operates directly in input space, making the anomaly score inherently feature-wise attributable; moreover, the score function is Lipschitz-continuous with respect to the input, providing theoretical guarantees under small perturbations. Extensive experiments on the ADBench benchmark show that TCCM strikes a favorable balance between detection accuracy and inference cost, outperforming state-of-the-art methods—especially on high-dimensional and large-scale datasets. The source code is provided at https: //github. com/ZhongLIFR/TCCM-NIPS.

PDF Details

NeurIPS Conference 2023 Conference Paper

On the Generalization Properties of Diffusion Models

Puheng Li
Zhong Li
Huishuai Zhang
Jiang Bian

Diffusion models are a class of generative models that serve to establish a stochastic transport map between an empirically observed, yet unknown, target distribution and a known prior. Despite their remarkable success in real-world applications, a theoretical understanding of their generalization capabilities remains underdeveloped. This work embarks on a comprehensive theoretical exploration of the generalization attributes of diffusion models. We establish the theoretical estimates of the generalization gap that evolves in tandem with the training dynamics of score-based diffusion models, suggesting a polynomially small generalization error ($O(n^{-2/5}+m^{-4/5})$) on both the sample size $n$ and the model capacity $m$, evading the curse of dimensionality (i. e. , independent of the data dimension) when *early-stopped*. Furthermore, we extend our quantitative analysis to a *data-dependent* scenario, wherein target distributions are portrayed as a succession of densities with progressively increasing distances between modes. This precisely elucidates the *adverse* effect of "*modes shift*'' in ground truths on the model generalization. Furthermore, these estimates are not solely theoretical constructs but have also been confirmed through numerical simulations. Our findings contribute to the rigorous understanding of diffusion models' generalization properties and provide insights that may guide practical applications.

PDF Details

NeurIPS Conference 2023 Conference Paper

OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects

Isabella Liu
Linghao Chen
Ziyang Fu
Liwen Wu
Haian Jin
Zhong Li
Chin Ming Ryan Wong
Yi Xu

We introduce OpenIllumination, a real-world dataset containing over 108K images of 64 objects with diverse materials, captured under 72 camera views and a large number of different illuminations. For each image in the dataset, we provide accurate camera parameters, illumination ground truth, and foreground segmentation masks. Our dataset enables the quantitative evaluation of most inverse rendering and material decomposition methods for real objects. We examine several state-of-the-art inverse rendering methods on our dataset and compare their performances. The dataset and code can be found on the project page: https: //oppo-us-research. github. io/OpenIllumination.

PDF Details

JMLR Journal 2022 Journal Article

Approximation and Optimization Theory for Linear Continuous-Time Recurrent Neural Networks

Zhong Li
Jiequn Han
Weinan E
Qianxiao Li

We perform a systematic study of the approximation properties and optimization dynamics of recurrent neural networks (RNNs) when applied to learn input-output relationships in temporal data. We consider the simple but representative setting of using continuous-time linear RNNs to learn from data generated by linear relationships. On the approximation side, we prove a direct and an inverse approximation theorem of linear functionals using RNNs, which reveal the intricate connections between memory structures in the target and the corresponding approximation efficiency. In particular, we show that temporal relationships can be effectively approximated by RNNs if and only if the former possesses sufficient memory decay. On the optimization front, we perform detailed analysis of the optimization dynamics, including a precise understanding of the difficulty that may arise in learning relationships with long-term memory. The term “curse of memory” is coined to describe the uncovered phenomena, akin to the “curse of dimension” that plagues high-dimensional function approximation. These results form a relatively complete picture of the interaction of memory and recurrent structures in the linear dynamical setting. [abs] [ pdf ][ bib ] &copy JMLR 2022. ( edit, beta )

PDF Details

ICML Conference 2021 Conference Paper

Testing DNN-based Autonomous Driving Systems under Critical Environmental Conditions

Zhong Li
Minxue Pan
Tian Zhang 0001
Xuandong Li

Due to the increasing usage of Deep Neural Network (DNN) based autonomous driving systems (ADS) where erroneous or unexpected behaviours can lead to catastrophic accidents, testing such systems is of growing importance. Existing approaches often just focus on finding erroneous behaviours and have not thoroughly studied the impact of environmental conditions. In this paper, we propose to test DNN-based ADS under different environmental conditions to identify the critical ones, that is, the environmental conditions under which the ADS are more prone to errors. To tackle the problem of the space of environmental conditions being extremely large, we present a novel approach named TACTIC that employs the search-based method to identify critical environmental conditions generated by an image-to-image translation model. Large-scale experiments show that TACTIC can effectively identify critical environmental conditions and produce realistic testing images, and meanwhile, reveal more erroneous behaviours compared to existing approaches.

Details

ICRA Conference 2013 Conference Paper

Rigid 2D space-filling folds of unbroken linear chains

Zhong Li
Devin J. Balkcom
Aaron M. Dollar

This paper presents an algorithm for folding a serial revolute chain into a rigid structure of essentially any desired planar shape. The algorithm is fast (linear in the number of links), and the constructed folding plan only requires an actuation method that sequentially folds triangles as the pattern is laid out, maintaining incremental rigidity of the structure during folding.

Details

TCS Journal 2011 Journal Article

The three column Bandpass problem is solvable in linear time

Zhong Li
Guohui Lin

The general Bandpass problem is NP-hard and was claimed to be NP-hard when the number of columns is three. Previously we designed a polynomial time row-stacking algorithm for the three column case, to produce a solution that is at most 1 less than the optimum. We show in this paper that for any bandpass number B ≥ 2, an optimal solution is always achievable in linear time.

Details DOI