Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks138 from public data
- DeepInception: Hypnotize Large Language Model to Be Jailbreaker438
A lightweight method to take advantage of the LLMs' personification capabilities to construct $\textit{a virtual, nested scene}$, allowing it to realize an adaptive way to escape the usage control in a normal scenario.
- Sparse-Interest Network for Sequential Recommendation192
A novel Sparse Interest NEtwork (SINE) is proposed, which develops an interest aggregation module to actively predict the user's current intention and then use it to explicitly model multiple interests for next-item prediction.
- Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI186
This survey is the first to set up the collaborative learning mechanism for cloud and edge modeling with a thorough review of the architectures that enable such mechanism, and discusses potentials and practical experiences of some on-going advanced edge AI topics including pretraining models, graph neural networks and reinforcement learning.
- Learning on Attribute-Missing Graphs149
This article makes a shared-latent space assumption on graphs and develops a novel distribution matching-based GNN called structure-attribute transformer (SAT) for attribute-missing graphs that shows better performance than other methods on both link prediction and node attribute completion tasks.
- 148
- 148
- Deep Learning From Noisy Image Labels With Quality Embedding140
A probabilistic model is proposed, which explicitly introduces an extra variable to represent the trustworthiness of noisy labels, termed as the quality variable, which effectively minimizes the influence of label noise and outperforms the state-of-the-art deep learning approaches.
- 136
- Class-Balancing Diffusion Models80
This work investigates the problem of significant degradation in both diversity and fidelity when the diffusion model is trained on datasets with classimbalanced distributions, and proposes Class-Balancing Diffusion Models (CBDM) that are trained with a distribution adjustment regularizer as a solution.
- Device-Cloud Collaborative Learning for Recommendation78
This work is among the first attempts to study the Device-Cloud Collaborative Learning (DCCL) framework and proposes a novel MetaPatch learning approach on the device side to efficiently achieve "thousands of people with thousands of models'' given a centralized cloud model.
- Safeguarded Dynamic Label Regression for Noisy Supervision61
This work proposes a Latent Class-Conditional Noise model (LCCN) that models the noise transition in a Bayesian form and specially deduce a dynamic label regression method for LCCN to iteratively infer the latent true labels and jointly train the classifier and model the noise.
- 55
- Collaborative Learning for Weakly Supervised Object Detection52
This paper proposes an end-to-end Weakly Supervised Collaborative Detection Network, which trains a weakly supervised learner and a strongly supervised learners jointly by enforcing partial feature sharing and prediction consistency.
- Synthesis of chiral N-aryl-α-amino acids by PdCu catalyzed couplings of chiral α-amino acids with aryl halides46
A concise synthesis of chiral N-aryl-α-amino acids, the common core structures for several biologically important molecules, by PdCu catalyzed coupling of L- or D-β-AMino acids and aryl halides is described.
- 41
- Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation40
This survey employs agnostic active sampling theory within the Probably Approximately Correct (PAC) framework to analyze the generalization error and label complexity associated with learning from low-resource data in both model-agnostic supervised and unsupervised settings.
- 36
- FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation35
This work introduces a data-driven approach called FedSkip to improve the client optima by periodically skipping federated averaging and scattering local models to the cross devices and provides theoretical analysis of the possible benefit from FedSkip.
- How Does Disagreement Benefit Co-teaching?32
Empirical results on noisy versions of MNIST, CIFAR-10 and NEWS demonstrate that Co-teaching+ is much superior to the state-of-the-art methods in the robustness of trained deep models.
- Bayes EMbedding (BEM)30
BEM is presented, a Bayesian framework that incorporates the information from knowledge graphs and behavior graphs and integrates them with the pre-trained embeddings from the behavior graphs via aBayesian generative model and is able to mutually refine the embeddeds from both sides while preserving their own topological structures.
- Preparation of 1,2-Diaryl(heteroaryl)pyrroles and -3-methylpyrroles from N-Allylbenzotriazole30
Numerous 1,2-diaryl(heteroaryl)pyrroles and -3-methylpyr roles were prepared in a two-step procedure from N-allylbenzotriazoles via intramolecular oxidative cyclization in the presence of Pd(II) catalyst.
- 29
- 28
- 25
- 25
- 24
- Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability22
A novel method is proposed, Unleashing Mask, which aims to restore the OOD discriminative capabilities of the well-trained model with ID data by utilizing a mask to figure out the memorized atypical samples, and then finetune the model or prune it with the introduced mask to forget them.
- Diversified Batch Selection for Training Acceleration21
Diversified Batch Selection (DivBS) is proposed, which is reference-model-free and can efficiently select diverse and representative samples and demonstrates the significant superiority of DivBS in the performance-speedup trade-off.
- 20
- 20
- 20
- Causal Distillation for Alleviating Performance Heterogeneity in Recommender Systems18
Through in-depth analysis, it is found that CausalD largely improves the performance of tail users, reduces the performance heterogeneity, and enhances the overall performance.
- 17
- Pumpout: A Meta Approach for Robustly Training Deep Neural Networks with Noisy Labels17
A meta algorithm called Pumpout is proposed to overcome the problem of memorizing noisy labels by using scaled stochastic gradient ascent, which actively squeezes out the negative effects of noisy labels from the training model, instead of passively forgetting these effects.
- 16
- 15
- Mitigating Label Noise on Graph via Topological Sample Selection15
A TSS method is proposed that boosts the informative sample selection process in a graph by utilising topological information and theoretically proves that the procedure minimizes an upper bound of the expected risk under target clean distribution, and experimentally shows the superiority of the method compared with state-of-the-art baselines.
- 14
- 14
- 13
- 13
- 13
- 13
- 12
- 12
- 11
- 11
- Learning with Group Noise11
This work proposes a novel Max-Matching method for learning with group noise that utilizes a matching mechanism to evaluate the relation confidence of each object w.r.t. the target, which considers the Non-IID characteristics among objects in the group.
- Combating Exacerbated Heterogeneity for Robust Models in Federated Learning10
A novel framework called Slack Federated Adversarial Training (SFAT), assigning the client-wise slack during aggregation to combat the intensified heterogeneity among local clients and properly relax the objective when combining federated learning and adversarial training is proposed.
- 9
- 9
- 8
- 8
- 8
- 8
- 7
- 7
- Towards Efficient Task-Driven Model Reprogramming with Foundation Models7
A Task-Driven Model Reprogramming (TDMR) framework that reprograms the foundation model to project the knowledge into a proxy space, which alleviates the adverse effect of task mismatch and domain inconsistency, and reprogram the target model via progressive distillation from the proxy space to efficiently learn the knowledge from the reprogrammed foundation model.
- Pumpout: A Meta Approach to Robust Deep Learning with Noisy Labels7
Pumpout is proposed as a meta approach to learning with noisy labels and an alternative to early stopping, and it is demonstrated via experiments that Pumpout robustifies two representative base learning methods, and the performance boost is often significant.
- 7
- 6
- Federated Learning under Partially Class-Disjoint Data via Manifold Reshaping6
This work proposes a manifold reshaping approach called FedMR, which adds two interplaying losses to the vanilla federated learning: one is intra-class loss to decorrelate feature dimensions for anti-collapse; and the other one is inter-class loss to guarantee the proper margin among categories in the feature expansion.
- 6
- 6
- 6
- 6
- 6
- Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning5
A new method, named Graph PU Learning with Label Propagation Loss (GPL), which considers learning from PU nodes along with an intermediate heterophily reduction, which helps mitigate the negative impact of the heterophilic structure.
- 5
- 5
- Serial Low-rank Adaptation of Vision Transformer4
Serial LoRA is proposed, a novel LoRA variant that introduces a shared low-rank matrix serially composite with the attention mechanism that extracts the underlying commonality of parameters in adaptation, significantly reducing redundancy.
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- Slack Federated Adversarial Training1
This work introduces an <inline-formula>-slack mechanism to relax the original learning objective of federated adversarial training, and proposes a novel framework called SFAT (SFAT) to combat the intensified heterogeneity.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Sandbox: safeguarded multi-label learning through safe optimal transport–
A novel Sandbox mechanism, which iteratively estimates multiple labels using an implicit optimal transport process, constraining label refinements between noisy labels and model predictions within a predefined polytope, effectively limiting error propagation, enhancing stability, and offering greater flexibility is introduced.
- –
- –
- –
- Exploring Model Dynamics for Accumulative Poisoning Discovery–
This paper dives into the perspective of model dynamics and proposes a novel information measure, namely, Memorization Discrepancy, to explore the defense via the model-level information and proposes Discrepancies-aware Sample Correction (DSC) to defend against accumulative poisoning attacks.
- –
- –
- –
- –
- –
- –
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 2026-10-13. 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.