Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks59 from public data
- Domain-Adversarial Network Alignment52
A unified deep architecture (DANA) is proposed to obtain a domain-invariant representation for network alignment via an adversarial domain classifier to achieve state-of-the-art alignment results.
- Toward Equivalent Transformation of User Preferences in Cross Domain Recommendation44
This article proposes an equivalent transformation learner (ETL), which models the joint distribution of user behaviors across domains and assumes that each user’s preferences in one domain can be expressed by the other one, and these preferences can be mutually converted to each other with the so-called equivalent transformation.
- 37
- 28
- PROUD: PaRetO-gUided diffusion model for multi-objective generation22
The ParetO-gUided Diffusion model (PROUD), wherein the gradients in the denoising process are dynamically adjusted to enhance generation quality while the generated samples adhere to Pareto optimality, is introduced.
- Max-Mahalanobis Anchors Guidance for Multi-View Clustering14
A novel method called Max-Mahalanobis Anchors Guidance for multi-view Clustering (MAGIC), which guides the cross-view representations to progressively align with well-defined anchors, significantly enhancing the performance of multi-view clustering.
- 14
- Robust Plackett–Luce model for k-ary crowdsourced preferences12
This paper presents a RObust PlAckett–Luce (ROPAL) model, and proposes an online Bayesian inference to make ROPAL scalable to large-scale preferences and achieves substantial improvements in robustness and noisy worker detection over current approaches.
- Reliable Facility Systems Design Subject to Edge Failures: Based on the Uncapacitated Fixed-Charge Location Problem11
Two models based on classical uncapacitated fixed-charge location problem under deterministic and stochastic cases are formulated and extensive experiments verify that significant improvements in reliability can be attained simply by increasing the amount of operating cost.
- White matter brain age as a biomarker of cerebrovascular burden in the ageing brain10
White matter specific brain age can be successfully targeted for the examination of the most relevant risk factors and cognition, and for tracking an individual's cerebrovascular ageing process, and provides clinical basis for the better management of specific risk factors.
- Association of Blood Pressure With Brain Ages: A Cohort Study of Gray and White Matter Aging Discrepancy in Mid-to-Older Adults From UK Biobank9
Compared with GM, WM was more vulnerable to raised BP, providing compelling evidence that concerted efforts should be directed towards WM damage in individuals with hypertension in clinical practice.
- 9
- Label Embedding with Partial Heterogeneous Contexts9
A general Partial Heterogeneous Context Label Embedding (PHCLE) framework, which overcomes the partial context problem and can nicely incorporate more contexts, which both cannot be tackled with existing multi-context label embedding methods.
- Coarse-to-Fine Contrastive Learning on Graphs7
This article first interpret CL as a special case of learning to rank (L2R), which inspires us to leverage the ranking order among positive augmented views and introduces a self-ranking paradigm to ensure that the discriminative information among different nodes can be maintained and also be less altered to the perturbations of different degrees.
- Learning Robust Node Representations on Graphs.6
The stability of node representations is introduced in addition to the smoothness and identifiability, and a novel method called contrastive graph neural networks (CGNN) is developed that learns robust node representations in an unsupervised manner.
- 5
- Sanitized clustering against confounding bias5
A new clustering framework named Sanitized Clustering Against confounding Bias is presented, which removes the confounding factor in the semantic latent space of complex data through a non-linear dependence measure.
- Learning node representations against perturbations5
A novel model called Stability-Identifiability GNN Against Perturbations (SIGNNAP) is proposed that learns reliable node representations in an unsupervised manner and preserves the \emph{smoothness} with existing GNN backbones.
- Online Mental Fatigue Monitoring via Indirect Brain Dynamics Evaluation5
Experimental results with 40 participants show that SWORE can maximally achieve consistent with RT, demonstrating the feasibility and adaptability of the proposed framework in practical mental fatigue estimation.
- Stochastic Multichannel Ranking with Brain Dynamics Preferences5
A novel channel-reliability-aware ranking (CArank) model for the multichannel ranking problem that learns from BDPs using EEG data robustly and aims at preserving the ordering corresponding to RTs, and introduces a transition matrix to characterize the reliability of each channel used in the EEG data.
- Stagewise learning for noisy k-ary preferences5
A reliable CrowdsOUrced Plackett–LucE (COUPLE) model combined with an efficient Bayesian learning technique is proposed, which achieves substantial improvements in reliability and noisy worker detection over other well-known approaches.
- Millionaire: a hint-guided approach for crowdsourcing5
This paper introduces the hint-guided approach into crowdsourcing, motivated by the “Guess-with-Hints” answer strategy from the Millionaire game show, and proposes a hybrid-stage setting, consisting of the main stage and the hint stage.
- Secure Metric Learning via Differential Pairwise Privacy4
For the first time, how pairwise information can be leaked to attackers during distance metric learning is studied, and differential pairwise privacy (DPP) is developed, generalizing the definition of standard differential privacy, for secure metric learning.
- Multiview Alignment and Generation in CCA via Consistent Latent Encoding4
This letter presents adversarial CCA (ACCA), which achieves consistent latent encodings by matching the marginalization of the joint distribution of multiview random variables under different forms of factorization, and reveals that ACCA is flexible for handling implicit distributions.
- Support Matching: A Novel Regularization to Escape from Mode Collapse in GANs4
Support Regularized-GAN (SR-GAN) is proposed to address the mode collapse issue of generative adversarial network by matching the support of the generated data distribution with that of the real data distribution.
- The Reward Model Selection Crisis in Personalized Alignment3
The findings reveal that the field has been optimizing for proxy metrics that do not predict deployment performance, and that current personalized alignment methods fail to operationalize preferences into behavioral adaptation under realistic deployment constraints, and finds simple in-context learning (ICL) to be highly effective.
- Earning Extra Performance From Restrictive Feedbacks3
This paper proposes to characterize the geometry of the model performance with regard to model parameters through exploring the parameters’ distribution, and suggests a more query-efficient algorithm is further tailor-designed that conducts layerwise tuning with more attention to those layers which pay off better.
- 2
- Taming Overconfident Prediction on Unlabeled Data From Hindsight2
This article proposes a dual mechanism, named adaptive sharpening (ADS), which first applies a soft-threshold to adaptively mask out determinate and negligible predictions, and then seamlessly sharpens the informed predictions, distilling certain predictions with the informed ones only.
- Differential-Critic GAN: Generating What You Want by a Cue of Preferences2
This article proposes differential-critic generative adversarial network (DiCGAN) to learn the distribution of user-desired data when only partial instead of the entire dataset possesses the desired property, and reformulates DiCGAN as a constrained optimization problem, based on which it theoretically prove the convergence of the DiCGAN.
- Multi-Context Label Embedding.2
This paper proposes a Multi-Context Label Embedding (MCLE) approach to incorporate multiple label contexts, e.g., label hierarchy and attributes, within a unified matrix factorization framework and imposes sparsity constraint on the multi-context framework to strengthen the interpretability of the learned label embedding.
- 1
- 1
- Group feature selection using non-class data1
It is proved that useful features can be identified through this non-class data that contribute to classifier construction and improved F∞\documentclass[12pt]{minimal}-norm support vector machine.
- 1
- HomRank: Homogeneous RNA Ranking for 3D Structure Evaluation1
The results demonstrate that carefully designed datasets and the expert-like selection paradigm can substantially improve the accuracy and robustness of RNA 3D structure assessment, offering a promising direction for deep learning-based RNA evaluation and near-native conformation selection.
- 1
- 1
- –
- –
- Learning Well-Structured Logits: Leveraging Vision–Language Complementarity for Open-World Test-Time Adaptation–
This paper decomposes OWTTA into two coupled modules: confidence-calibrated filtering (CCF), which provides an estimate of in-distribution membership, and semantic complementarity adaptation (SCA), which gives the refined predictions through complementary logit fusion.
- –
- –
- Auto-Clustering with Continuous Distribution Estimation on Centroids–
This work introduces a fit-then-prune strategy, named auto-ClusTering (ACT), equipped with continuous centroid distribution estimation, and delivers an equivalent but succinct centroid distribution by safely pruning redundant particles, inferring the cluster number close to the true one.
- –
- From Structure to Function: Preference Alignment for Function-aware Protein Inverse Folding–
A function-aware preference alignment framework that improves functional preservation by fine-tuning models to favor function-preserving sequences over function-disrupting alternatives, avoiding the need for explicit function optimization.
- –
- Alpha and Prejudice: Improving α-Sized Worst Case Fairness via Intrinsic Reweighting–
A reweighting approach that assigns sample weights based on their intrinsic contributions to fairness based on their intrinsic contributions to fairness is proposed, and a stochastic learning algorithm is developed that simplifies training without sacrificing performance.
- –
- Leveraging Scene Context with Dual Networks for Sequential User Behavior Modeling–
Theoretical analysis suggests that DSPnet is a principled way to learn the joint relationships between scene and item sequences, and a Conditional Contrastive Regularization (CCR) loss to capture the invariance of similar historical sequences.
- –
- –
- Deep learning-derived age of hippocampus-centred regions is influenced by APOE genotype and modifiable risk factors–
Occlusion analysis saliency maps indicated that regions around the hippocampus, including the thalamus, pallidum, nearby cerebral cortex, and white matter, significantly contributed to the age prediction and the left HA gap emerges as a potential biomarker linked to the APOE genotype and an indicator of health.
- –
- –
- –
- –
- Mental Fatigue Monitoring using Brain Dynamics Preferences–
Comprehensive empirical analysis on EEG signals from 44 participants shows that BDrank together with OnlineGEM achieves substantial improvements in reliability while simultaneously detecting possible less informative and noisy EEG channels.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-10. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.