Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks243 from public data
- Disentangled Graph Convolutional Networks387
This paper introduces the disentangled graph convolutional network (DisenGCN) to learn disentangled node representations and proposes a novel neighborhood routing mechanism, which is capable of dynamically identifying the latent factor that may have caused the edge between a node and one of its neighbors and accordingly assigning the neighbor to a channel that extracts and convolutes features to that factor.
- BertGCN: Transductive Text Classification by Combining GNN and BERT329
BertGCN constructs a heterogeneous graph over the dataset and represents documents as nodes using BERT representations and GCN modules within BertGCN, a model that combines large scale pretraining and transductive learning for text classification.
- Stable Prediction across Unknown Environments198
This paper proposes a novel Deep Global Balancing Regression (DGBR) algorithm to jointly optimize a deep auto-encoder model for feature selection and a global balancing model for stable prediction across unknown environments, and demonstrates that the algorithm outperforms the state-of-the-art methods for stable predictions acrossunknown environments.
- 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.
- Federated unsupervised representation learning174
The federated contrastive averaging with dictionary and alignment (FedCA) algorithm, composed of two key modules: a dictionary module to aggregate the representations of samples from each client which can be shared with all clients for consistency of representation space, is adopted for local model training.
- Stable Prediction with Model Misspecification and Agnostic Distribution Shift163
A novel Decorrelated Weighting Regression algorithm which jointly optimizes a variable decorrelation regularizer and a weighted regression model to improve the accuracy of parameter estimation and stability of prediction with model misspecification and agnostic distribution shift.
- Causal Inference126
This review covers developments in both causal identification and causal effect estimation, and discusses the type of assumptions and questions frequently encountered in empirical research, ending with a discussion of promising new directions in the field.
- Causally Regularized Learning with Agnostic Data Selection Bias105
Under the assumption that causal relationships among variables are robust across domains, this paper incorporates causal technique into predictive modeling and proposes a novel Causally Regularized Logistic Regression (CRLR) algorithm by jointly optimize global confounder balancing and weighted logistic regression.
- De-Biased Court’s View Generation with Causality101
A novel Attentional and Counterfactual based Natural Language Generation (AC-NLG) method, consisting of an attentional encoder and a pair of innovative counterfactual decoders, to eliminate the confounding bias in data and generate judgment-discriminative court’s views by incorporating with a synergistic judgment predictive model.
- Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning98
Sh Shapley Counterfactual Credit Assignment is proposed, a novel method for explicit credit assignment which accounts for the coalition of agents and outperforms existing cooperative MARL algorithms significantly and achieves the state-of-the-art.
- 93
- Treatment Effect Estimation with Data-Driven Variable Decomposition81
Under standard assumptions, it is shown experimentally that the proposed D$^2$VD algorithm can automatically separate the variables precisely, and estimate treatment effect more accurately and with tighter confidence intervals than the state-of-the-art methods on both synthetic data and real online advertising dataset.
- Estimating Treatment Effect in the Wild via Differentiated Confounder Balancing80
A data-driven Differentiated Confounder Balancing (DCB) algorithm to jointly select confoundingers, differentiate weights of confounders and balance confounder distributions for treatment effect estimation in the wild high dimensional settings is proposed.
- Judgment Prediction via Injecting Legal Knowledge into Neural Networks79
This paper proposes to represent declarative legal knowledge as a set of first-order logic rules and integrate these logic rules into a co-attention network-based model explicitly, which enhances neural networks with explicit logical reason capabilities and makes the model more interpretable.
- DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization72
It is argued that the computational cost brought by fine-tuning can be rather unnecessary, and a novel perspective to improving DMG without increasing computational cost is presented, i.e., device-specific parameter generation which directly maps data distribution to parameters.
- 69
- Analysis and Applications of Class-wise Robustness in Adversarial Training60
This work proposes to analyze the class-wise robustness in adversarial training and proposes a simple but effective attack method, named Temperature-PGD attack, which proposes to enlarge the robustness disparity among classes with a temperature factor on the confidence distribution of each image.
- ML-LJP: Multi-Law Aware Legal Judgment Prediction59
Following the actual legal process, the law article prediction is expanded as a multi-label classification task that includes both the charge-related law articles and term-relatedlaw articles and a novel multi-law aware LJP (ML-LJP) method is proposed to improve the performance of LJP.
- 55
- Intelligent Model Update Strategy for Sequential Recommendation55
IntellectReq is a novel learning task, aimed at the detection of out-of-distribution data, thereby fine-tuning adaptive communication strategies and evidencing a marked improvement in the efficiency and generalizability of edge-cloud collaborative and dynamic recommendation systems.
- Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition55
A novel Automatic Instrumental Variable decomposition (AutoIV) algorithm to automatically generate representations serving the role of IVs from observed variables (IV candidates) via mutual information maximization and minimization constraints.
- Debiased Graph Neural Networks With Agnostic Label Selection Bias54
A novel debiased GNNs (DGNN) with a differentiated decorrelation regularizer is proposed, which outperforms the state-of-the-art methods and DGNN is a flexible framework to enhance existing GNN's.
- Towards Interactivity and Interpretability: A Rationale-based Legal Judgment Prediction Framework53
This paper proposes a novel Rationale-based Legal Judgment Prediction (RLJP) framework, which provides good interactivity and interpretability which enables practical use and achieves the best results compared to the state-of-the-art models.
- Federated mutual learning: a collaborative machine learning method for heterogeneous data, models, and objectives51
An overview of the heterogeneities in data, model, and objective (DMO) is provided and a novel framework called federated mutual learning (FML) is proposed, which enables each client to train a personalized model that accounts for the data heterogeneity (DH).
- Unified fair federated learning for digital healthcare51
This work proposes Federated Learning with Unified Fairness Objective (FedUFO), a unified framework consolidating diverse fairness levels within FL that ensures consistent performance across all subpopulations and enhances the overall efficacy of FL in healthcare and other domains while maintaining accuracy levels comparable with those of existing methods.
- 49
- 49
- 46
- 44
- Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards42
A novel RL-based framework that addresses the sparse reward problem when training diffusion models, named B2-DiffuRL, which employs two strategies: Backward progressive training and Branch-based sampling.
- 42
- Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation35
The Device-Cloud LLM-SRM Collaborative Recommendation Framework (LSC4Rec) is designed under a device-cloud collaboration setting and aims to integrate the advantages of both LLMs and SRMs, as well as the benefits of cloud and edge computing, achieving a complementary synergy.
- 32
- Semantic Alignment for Multimodal Large Language Models31
Semantic Alignment for Multi-modal large language models (SAM) is introduced, which aims to enhance the preservation of linking information for coherent analysis and align the semantics of different images before feeding them into LLM.
- 30
- 29
- 29
- 28
- 26
- 26
- 25
- Dependency Parsing as MRC-based Span-Span Prediction24
The proposed method addresses the fundamental problem that edges in a dependency tree should be constructed between subtrees and the MRC framework allows the method to retrieve missing spans in the span proposal stage, which leads to higher recall for eligible spans.
- 24
- 23
- 21
- 21
- 20
- 20
- 20
- Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning18
Retrieval-Augmented Mixture of LoRA Experts (RAMoLE), a framework that adaptively retrieves and composes multiple LoRAs based on input prompts, is proposed, highlighting its effectiveness and scalability.
- 18
- 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.
- Exploiting Contrastive Learning and Numerical Evidence for Confusing Legal Judgment Prediction18
A moco-based supervised contrastive learning to learn distinguishable representations is proposed, and the best strategy to construct positive example pairs to benefit all three subtasks of LJP simultaneously is explored.
- D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples17
D-Fusion is introduced, a method to construct DPO-trainable visually consistent samples that can retain the denoising trajectories of the resulting images, which are essential for DPO training and improving prompt-image alignment when applied to different reinforcement learning algorithms.
- 17
- Who Should Be Given Incentives? Counterfactual Optimal Treatment Regimes Learning for Recommendation16
- SLED: Structure Learning based Denoising for Recommendation16
It is identified that an interaction’s related structural patterns in its neighborhood graph are potentially correlated with some outcome of implicit feedback (i.e., users’ ratings after consuming items), analogous to findings in other domains such as social networks.
- 16
- 16
- Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond15
This work presents the first systematic evaluation of 12 LLMs, including both reasoning-focused and general-purpose models, across 17 Chinese and English legal tasks spanning statutory and case-law traditions and develops Legal-R1, an open-source model specialized for the legal domain.
- 15
- 15
- Distributionally Generative Augmentation for Fair Facial Attribute Classification14
This work proposes a novel, generation-based two-stage framework to train a fair FAC model on biased data without additional annotation, and enhances interpretability by explicitly showing the spurious attributes in image space.
- 14
- 13
- 13
- 12
- 12
- 12
- 12
- 12
- Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts11
HEI is proposed, a framework capable of generating invariant node representations through incorporating Heterophily information, the node's estimated neighbor pattern, to infer latent Environments without augmentation, which are then used for Invariant prediction.
- Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning11
This paper explores a methodology for reward composition that enables simultaneous improvements in LMs across multiple dimensions and introduces a training algorithm that aims to reduce disparity and enhance stability among various rewards.
- 11
- 11
- 11
- 10
- 9
- 9
- 9
- Uncovering Causal Effects of Online Short Videos on Consumer Behaviors9
Both causal effects (i.e., informative and persuasive effects) are significant and have a strong correlation with the short videos' subjectivity scores, and the signs of these correlations vary with the prices of the products.
- 9
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- Collaborative Intelligence Orchestration: Inconsistency-Based Fusion of Semi-Supervised Learning and Active Learning4
An innovative Inconsistency-based virtual aDvErsarial Active Learning (IDEAL) algorithm to further investigate SSL-AL's potential superiority and achieve mutual enhancement of AL and SSL, i.e., SSL propagates label information to unlabeled samples and provides smoothed embeddings for AL, while AL excludes samples with inconsistent predictions and considerable uncertainty for SSL.
- 4
- 4
- 4
- 4
- 4
- 3
- Legal Judgment Prediction based on Knowledge-enhanced Multi-Task and Multi-Label Text Classification3
- Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation3
A novel framework that allocates distinct timesteps to different pixels and reformulates the pixel-wise denoising process is proposed -- a novel framework that allocates distinct timesteps to different pixels and reformulates the pixel-wise denoising process to improve text-to-image alignment.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- MGD-GAN: Text-to-Pedestrian Generation Through Multi-grained Discrimination2
The Multi-Grained Discrimination enhanced Generative Adversarial Network (MGD-GAN) is proposed, that capitalizes a human-part-based Discriminator (HPD) and a self-cross-attended (SCA) global Discriminators in order to capture the coherence of the complex body structure.
- 2
- 1
- 1
- 1
- Tackling Device Data Distribution Real-time Shift via Prototype-based Parameter Editing1
Persona is a novel personalized method using a prototype-based, backpropagation-free parameter editing framework to enhance model generalization without post-deployment retraining to tackle the generalization of lightweight on-device models.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- Learning Kernelized Hypothesis for Hidden Confounder Detection–
A Bi-level Kernel Confounder Detection (BiKCD) framework is contributed by learning adaptive kernelized structural space of structural functions by comparing coefficients from the higher-order regression and the classical ordinary least squares in learned kernelized space.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.