Jianhui Chen

ECAI Conference 2025 Conference Paper

Deep Bilateral Intensity-Position Registration for Autonomous Ureteroscopic Navigation

• Xiangtao Du
• Wenkang Fan
• Hao Fang
• Jianhui Chen
• Song Zheng
• Guangcheng Luo
• Xiongbiao Luo

Flexible ureteroscopy is a routinely performed surgical procedure to treat renal disorders such as tumors and stones, but it gets trapped in precisely orientating the ureteroscope in the complex kidneys. To facilitate ureteroscopic procedures, we propose employing deep learning techniques for preliminary data processing and propose a new ureteroscopic navigation framework that uses deeply learned bilateral 2D-3D registration. Specifically, a new structural intensity-position similarity function is formulated to characterize the difference between 2D ureteroscopic video sequences and preoperative computed tomography urography images. While we propose a small deep learning model of deformable large-kernel convolutional networks without any transformer blocks to segment the urinary collecting system from preoperative images, we employ dense prediction transformers and a color model of hue-saturation-value to extract structural regions from ureteroscopic video sequences. The new cost function is designed by the dice similarity coefficient and structural similarity index to calculate the pixel intensity and position (coordinate) differences. We validated our method on clinical data collected from different patients in the operating room, with the experimental results showing that our method outperforms state-of-the-art registration approaches, reducing the navigation errors from (7. 8 mm, 10. 7°) to (7. 1 mm, 9. 7°).

NeurIPS Conference 2025 Conference Paper

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons

• Jianhui Chen
• Xiaozhi Wang
• Zijun Yao
• Yushi Bai
• Lei Hou
• Juanzi Li

Large language models (LLMs) excel in various capabilities but pose safety risks such as generating harmful content and misinformation, even after safety alignment. In this paper, we explore the inner mechanisms of safety alignment through the lens of mechanistic interpretability, focusing on identifying and analyzing safety neurons within LLMs that are responsible for safety behaviors. We propose inference-time activation contrasting to locate these neurons and dynamic activation patching to evaluate their causal effects on model safety. Experiments on multiple prevalent LLMs demonstrate that we can consistently identify about 5% safety neurons, and by only patching their activations we can restore over 90% of the safety performance across various red-teaming benchmarks without influencing general ability. The finding of safety neurons also helps explain the ''alignment tax'' phenomenon by revealing that the key neurons for model safety and helpfulness significantly overlap, yet they require different activation patterns for the same neurons. Furthermore, we demonstrate an application of our findings in safeguarding LLMs by detecting unsafe outputs before generation.

ICLR Conference 2024 Conference Paper

KoLA: Carefully Benchmarking World Knowledge of Large Language Models

• Jifan Yu
• Xiaozhi Wang
• Shangqing Tu
• Shulin Cao
• Daniel Zhang-Li
• Xin Lv
• Hao Peng 0015
• Zijun Yao 0002

The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations. Rather than merely exploring the breadth of LLM abilities, we believe meticulous and thoughtful designs are essential to thorough, unbiased, and applicable evaluations. Given the importance of world knowledge to LLMs, we construct a Knowledge-oriented LLM Assessment benchmark (KoLA), in which we carefully design three crucial factors: (1) For ability modeling, we mimic human cognition to form a four-level taxonomy of knowledge-related abilities, covering 19 tasks. (2) For data, to ensure fair comparisons, we use both Wikipedia, a corpus prevalently pre-trained by LLMs, along with continuously collected emerging corpora, aiming to evaluate the capacity to handle unseen data and evolving knowledge. (3) For evaluation criteria, we adopt a contrastive system, including overall standard scores for better numerical comparability across tasks and models, and a unique self-contrast metric for automatically evaluating knowledge-creating ability. We evaluate 21 open-source and commercial LLMs and obtain some intriguing findings. The KoLA dataset will be updated every three months to provide timely references for developing LLMs and knowledge-related systems.

AAAI Conference 2017 Conference Paper

A Framework of Online Learning with Imbalanced Streaming Data

• Yan Yan
• Tianbao Yang
• Yi Yang
• Jianhui Chen

A challenge for mining large-scale streaming data overlooked by most existing studies on online learning is the skewdistribution of examples over different classes. Many previous works have considered cost-sensitive approaches in an online setting for streaming data, where fixed costs are assigned to different classes, or ad-hoc costs are adapted based on the distribution of data received so far. However, it is not necessary for them to achieve optimal performance in terms of the measures suited for imbalanced data, such as Fmeasure, area under ROC curve (AUROC), area under precision and recall curve (AUPRC). This work proposes a general framework for online learning with imbalanced streaming data, where examples are coming sequentially and models are updated accordingly on-the-fly. By simultaneously learning multiple classifiers with different cost vectors, the proposed method can be adopted for different target measures for imbalanced data, including F-measure, AUROC and AUPRC. Moreover, we present a rigorous theoretical justification of the proposed framework for the F-measure maximization. Our empirical studies demonstrate the competitive if not better performance of the proposed method compared to previous cost-sensitive and resampling based online learning algorithms and those that are designed for optimizing certain measures.

IROS Conference 2017 Conference Paper

Backtracking regression forests for accurate camera relocalization

• Lili Meng
• Jianhui Chen
• Frederick Tung
• James J. Little
• Julien Valentin
• Clarence W. de Silva

Camera relocalization plays a vital role in many robotics and computer vision tasks, such as global localization, recovery from tracking failure, and loop closure detection. Recent random forests based methods directly predict 3D world locations for 2D image locations to guide the camera pose optimization. During training, each tree greedily splits the samples to minimize the spatial variance. However, these greedy splits often produce uneven sub-trees in training or incorrect 2D-3D correspondences in testing. To address these problems, we propose a sample-balanced objective to encourage equal numbers of samples in the left and right sub-trees, and a novel backtracking scheme to remedy the incorrect 2D-3D correspondence predictions. Furthermore, we extend the regression forests based methods to use local features in both training and testing stages for outdoor RGB-only applications. Experimental results on publicly available indoor and outdoor datasets demonstrate the efficacy of our approach, which shows superior or on-par accuracy with several state-of-the-art methods.

AAAI Conference 2017 Conference Paper

Efficient Ordered Combinatorial Semi-Bandits for Whole-Page Recommendation

• Yingfei Wang
• Hua Ouyang
• Chu Wang
• Jianhui Chen
• Tsvetan Asamov
• Yi Chang

Multi-Armed Bandit (MAB) framework has been successfully applied in many web applications. However, many complex real-world applications that involve multiple content recommendations cannot fit into the traditional MAB setting. To address this issue, we consider an ordered combinatorial semi-bandit problem where the learner recommends S actions from a base set of K actions, and displays the results in S (out of M) different positions. The aim is to maximize the cumulative reward with respect to the best possible subset and positions in hindsight. By the adaptation of a minimumcost maximum-flow network, a practical algorithm based on Thompson sampling is derived for the (contextual) combinatorial problem, thus resolving the problem of computational intractability. With its potential to work with whole-page recommendation and any probabilistic models, to illustrate the effectiveness of our method, we focus on Gaussian process optimization and a contextual setting where click-throughrate is predicted using logistic regression. We demonstrate the algorithms’ performance on synthetic Gaussian process problems and on large-scale news article recommendation datasets from Yahoo! Front Page Today Module.

UAI Conference 2016 Conference Paper

Optimal Stochastic Strongly Convex Optimization with a Logarithmic Number of Projections

• Jianhui Chen
• Tianbao Yang
• Qihang Lin
• Lijun Zhang 0005
• Yi Chang 0001

We consider stochastic strongly convex optimization with a complex inequality constraint. This complex inequality constraint may lead to computationally expensive projections in algorithmic iterations of the stochastic gradient descent (SGD) methods. To reduce the computation costs pertaining to the projections, we propose an Epoch-Projection Stochastic Gradient Descent (Epro-SGD) method. The proposed Epro-SGD method consists of a sequence of epochs; it applies SGD to an augmented objective function at each iteration within the epoch, and then performs a projection at the end of each epoch. Given a strongly convex optimization and for a total number of T iterations, Epro-SGD requires only log(T ) projections, and meanwhile attains an optimal convergence rate of O(1/T ), both in expectation and with a high probability. To exploit the structure of the optimization problem, we propose a proximal variant of EproSGD, namely Epro-ORDA, based on the optimal regularized dual averaging method. We apply the proposed methods on real-world applications; the empirical results demonstrate the effectiveness of our methods.

AAAI Conference 2015 Conference Paper

Exploiting Task-Feature Co-Clusters in Multi-Task Learning

• Linli Xu
• Aiqing Huang
• Jianhui Chen
• Enhong Chen

In multi-task learning, multiple related tasks are considered simultaneously, with the goal to improve the generalization performance by utilizing the intrinsic sharing of information across tasks. This paper presents a multitask learning approach by modeling the task-feature relationships. Specifically, instead of assuming that similar tasks have similar weights on all the features, we start with the motivation that the tasks should be related in terms of subsets of features, which implies a co-cluster structure. We design a novel regularization term to capture this task-feature co-cluster structure. A proximal algorithm is adopted to solve the optimization problem. Convincing experimental results demonstrate the effectiveness of the proposed algorithm and justify the idea of exploiting the task-feature relationships.

IS Journal 2014 Journal Article

WaaS: Wisdom as a Service

• Jianhui Chen
• Jianhua Ma
• Ning Zhong
• Yiyu Yao
• Jiming Liu
• Runhe Huang
• Wenbin Li
• Zhisheng Huang

An emerging hyper-world encompasses all human activities in a social-cyber-physical space. Its power derives from the Wisdom Web of Things (W2T) cycle, namely, "from things to data, information, knowledge, wisdom, services, humans, and then back to things. "' The W2T cycle leads to a harmonious symbiosis among humans, computers, and things, which can be constructed by large-scale converging of intelligent information technology applications with an open and interoperable architecture. The recent advances in cloud computing, the Internet of Things, Web of Things, Big Data, and other research fields have provided just such an open system architecture with resource sharing and services. The next step is to develop an open and interoperable content architecture with intelligent sharing and services for the organization and transformation in the data, information, knowledge, and wisdom (DIKW) hierarchy. This article introduces wisdom as a service (WaaS), a content architecture based on the pay-as-you-go IT trend. The WaaS infrastructure and the main challenges in WaaS research and applications are discussed. A case study is also described. Relying on cloud computing and big data, WaaS provides a practical approach to realize the W2T cycle in the hyper-world for the coming age of ubiquitous intelligent IT applications.

NeurIPS Conference 2011 Conference Paper

Clustered Multi-Task Learning Via Alternating Structure Optimization

• Jiayu Zhou
• Jianhui Chen
• Jieping Ye

Multi-task learning (MTL) learns multiple related tasks simultaneously to improve generalization performance. Alternating structure optimization (ASO) is a popular MTL method that learns a shared low-dimensional predictive structure on hypothesis spaces from multiple related tasks. It has been applied successfully in many real world applications. As an alternative MTL approach, clustered multi-task learning (CMTL) assumes that multiple tasks follow a clustered structure, i. e. , tasks are partitioned into a set of groups where tasks in the same group are similar to each other, and that such a clustered structure is unknown a priori. The objectives in ASO and CMTL differ in how multiple tasks are related. Interestingly, we show in this paper the equivalence relationship between ASO and CMTL, providing significant new insights into ASO and CMTL as well as their inherent relationship. The CMTL formulation is non-convex, and we adopt a convex relaxation to the CMTL formulation. We further establish the equivalence relationship between the proposed convex relaxation of CMTL and an existing convex relaxation of ASO, and show that the proposed convex CMTL formulation is significantly more efficient especially for high-dimensional data. In addition, we present three algorithms for solving the convex CMTL formulation. We report experimental results on benchmark datasets to demonstrate the efficiency of the proposed algorithms.

IJCAI Conference 2009 Conference Paper

• Lei Tang
• Jianhui Chen
• Jieping Ye

For classification with multiple labels, a common approach is to learn a classifier for each label. With a kernel-based classifier, there are two options to set up kernels: select a specific kernel for each label or the same kernel for all labels. In this work, we present a unified framework for multi-label multiple kernel learning, in which the above two approaches can be considered as two extreme cases. Moreover, our framework allows the kernels shared partially among multiple labels, enabling flexible degrees of label commonality. We systematically study how the sharing of kernels among multiple labels affects the performance based on extensive experiments on various benchmark data including images and microarray data. Interesting findings concerning efficacy and efficiency are reported.

IJCAI Conference 2009 Conference Paper

• Jun Liu
• Jianhui Chen
• Songcan Chen
• Jieping Ye

Kernel methods have been applied successfully in many applications. The kernel matrix plays an important role in kernel-based learning methods, but the “ideal” kernel matrix is usually unknown in practice and needs to be estimated. In this paper, we propose to directly learn the “ideal” kernel matrix (called the optimal neighborhood kernel matrix) from a pre-specified kernel matrix for improved classification performance. We assume that the prespecified kernel matrix generated from the specific application is a noisy observation of the ideal one. The resulting optimal neighborhood kernel matrix is shown to be the summation of the pre-specified kernel matrix and a rank-one matrix. We formulate the problem of learning the optimal neighborhood kernel as a constrained quartic problem, and propose to solve it using two methods: level method and constrained gradient descent. Empirical results on several benchmark data sets demonstrate the efficiency and effectiveness of the proposed algorithms.

ICML Conference 2009 Conference Paper

A convex formulation for learning shared structures from multiple tasks

• Jianhui Chen
• Lei Tang 0001
• Jun Liu 0003
• Jieping Ye

NeurIPS Conference 2009 Conference Paper

Efficient Recovery of Jointly Sparse Vectors

• Liang Sun
• Jun Liu
• Jianhui Chen
• Jieping Ye

We consider the reconstruction of sparse signals in the multiple measurement vector (MMV) model, in which the signal, represented as a matrix, consists of a set of jointly sparse vectors. MMV is an extension of the single measurement vector (SMV) model employed in standard compressive sensing (CS). Recent theoretical studies focus on the convex relaxation of the MMV problem based on the $(2, 1)$-norm minimization, which is an extension of the well-known $1$-norm minimization employed in SMV. However, the resulting convex optimization problem in MMV is significantly much more difficult to solve than the one in SMV. Existing algorithms reformulate it as a second-order cone programming (SOCP) or semidefinite programming (SDP), which is computationally expensive to solve for problems of moderate size. In this paper, we propose a new (dual) reformulation of the convex optimization problem in MMV and develop an efficient algorithm based on the prox-method. Interestingly, our theoretical analysis reveals the close connection between the proposed reformulation and multiple kernel learning. Our simulation studies demonstrate the scalability of the proposed algorithm.

JMLR Journal 2008 Journal Article

Multi-class Discriminant Kernel Learning via Convex Programming

• Jieping Ye
• Shuiwang Ji
• Jianhui Chen

Regularized kernel discriminant analysis (RKDA) performs linear discriminant analysis in the feature space via the kernel trick. Its performance depends on the selection of kernels. In this paper, we consider the problem of multiple kernel learning (MKL) for RKDA, in which the optimal kernel matrix is obtained as a linear combination of pre-specified kernel matrices. We show that the kernel learning problem in RKDA can be formulated as convex programs. First, we show that this problem can be formulated as a semidefinite program (SDP). Based on the equivalence relationship between RKDA and least square problems in the binary-class case, we propose a convex quadratically constrained quadratic programming (QCQP) formulation for kernel learning in RKDA. A semi-infinite linear programming (SILP) formulation is derived to further improve the efficiency. We extend these formulations to the multi-class case based on a key result established in this paper. That is, the multi-class RKDA kernel learning problem can be decomposed into a set of binary-class kernel learning problems which are constrained to share a common kernel. Based on this decomposition property, SDP formulations are proposed for the multi-class case. Furthermore, it leads naturally to QCQP and SILP formulations. As the performance of RKDA depends on the regularization parameter, we show that this parameter can also be optimized in a joint framework with the kernel. Extensive experiments have been conducted and analyzed, and connections to other algorithms are discussed. [abs] [ pdf ][ bib ] &copy JMLR 2008. ( edit, beta )

ICML Conference 2008 Conference Paper

Training SVM with indefinite kernels

• Jianhui Chen
• Jieping Ye

ICML Conference 2007 Conference Paper

Discriminant kernel and regularization parameter learning via semidefinite programming

• Jieping Ye
• Jianhui Chen
• Shuiwang Ji

Regularized Kernel Discriminant Analysis (RKDA) performs linear discriminant analysis in the feature space via the kernel trick. The performance of RKDA depends on the selection of kernels. In this paper, we consider the problem of learning an optimal kernel over a convex set of kernels. We show that the kernel learning problem can be formulated as a semidefinite program (SDP) in the binary-class case. We further extend the SDP formulation to the multi-class case. It is based on a key result established in this paper, that is, the multi-class kernel learning problem can be decomposed into a set of binary-class kernel learning problems. In addition, we propose an approximation scheme to reduce the computational complexity of the multi-class SDP formulation. The performance of RKDA also depends on the value of the regularization parameter. We show that this value can be learned automatically in the framework. Experimental results on benchmark data sets demonstrate the efficacy of the proposed SDP formulations.