Jiaqi Lv

Prof. Dr. Jiaqi Lv


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 May 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
JLJiaqi Lv
Jiaqi Lv
BLBiao Liu
Biao Liu
LFLei Feng
Lei Feng
NXNing Xu
Ning Xu
MXMiao Xu
Miao Xu
MSMasashi Sugiyama
Masashi Sugiyama
Partial-label learning (PLL) utilizes instances with PLs, where a PL includes several candidate labels but only one is the true label (TL). In PLL, identification-based strategy (IBS) purifies each PL on the fly to select the (most likely) TL for training; average-based strategy (ABS) treats all candidate labels equally for training and let trained models be able to predict TL. Although PLL research has focused on IBS for better performance, ABS is also worthy of study since modern IBS behaves like ABS in the beginning of training to prepare for PL purification and TL selection. In this paper, we analyze why ABS was unsatisfactory and propose how to improve it. Theoretically, we propose two problem settings of PLL and prove that average PL losses (APLLs) with bounded multi-class losses are always robust, while APLLs with unbounded losses may be non-robust, which is the first robustness analysis for PLL. Experimentally, we have two promising findings: ABS using bounded losses can match/exceed state-of-the-art performance of IBS using unbounded losses; after using robust APLLs to warm start, IBS can further improve upon itself. Our work draws attention to ABS research, which can in turn boost IBS and push forward the whole PLL.

2 April 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
Xin GengXin Geng
Xin Geng
RZRenyi Zheng
Renyi Zheng
JLJiaqi Lv
Jiaqi Lv
YZYu Zhang
Yu Zhang
While most existing multilabel ranking methods assume the availability of a single objective label ranking for each instance in the training set, this paper deals with a more common case where only subjective inconsistent rankings from multiple rankers are associated with each instance. Two ranking methods are proposed from the perspective of instances and rankers, respectively. The first method, Instance-oriented Preference Distribution Learning (IPDL), is to learn a latent preference distribution for each instance. IPDL generates a common preference distribution that is most compatible to all the personal rankings, and then learns a mapping from the instances to the preference distributions. The second method, Ranker-oriented Preference Distribution Learning (RPDL), is proposed by leveraging interpersonal inconsistency among rankers, to learn a unified model from personal preference distribution models of all rankers. These two methods are applied to natural scene images dataset and 3D facial expression dataset BU_3DFE. Experimental results show that IPDL and RPDL can effectively incorporate the information given by the inconsistent rankers, and perform remarkably better than the compared state-of-the-art multilabel ranking algorithms.

17 November 2026 in Electronics
Verified
Journal Article
Open access
PDF file
JLJiaqi Lv
Jiaqi Lv
QYQingxia Yang
Qingxia Yang
XLXingyu Lu
Xingyu Lu
Partial-label learning aims to learn from ambiguous supervision, where each instance is annotated with a set of candidate labels that contain only one correct class. While recent advances rely on local discriminative objectives to enhance representation quality, they often overlook the global structure of the representation space, leading to greater relative dispersion in inter-class representation differences, which may impair generalization. In this work, we propose RDAP (Representation Difference Alignment for Partial-Label Learning), a structure-aware regularization framework that regularizes the relative dispersion of inter-class representation differences using predicted label distributions, without requiring ground-truth labels. RDAP introduces a novel alignment loss guided by distribution-level dissimilarity between predicted labels, combined with stochastic representation masking to reduce computational cost. RDAP is fully compatible with existing PLL pipelines and can be seamlessly integrated without architectural modifications. Extensive experiments across diverse datasets and candidate-label protocols show that RDAP can enhance structural representation quality and achieve competitive classification performance across a range of partial-label learning benchmarks.