Author name cluster

Shifei Ding

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

1 author row

IJCAI Conference 2025 Conference Paper

A Medical Image Classification Network Based on Multi-View Consistent Momentum Contrastive Learning

Chuangui Cao
Shifei Ding
Lili Guo

Due to variations in imaging conditions, images often exhibit discrepancies in color reproduction. Furthermore, motion-induced blur can lead to edge degradation, making color sensitivity and edge blurriness two prevalent and challenging issues in both natural image processing and medical image analysis. To address these challenges, we propose a model termed the Three-View Consistency Mo-mentum Contrastive with Sobel Operator (SVCMC). Specifically, we first design a three-view momen-tum-update architecture that employs a So-bel-augmented ResNet as the backbone. We then introduce a novel contrastive loss, referred to as the Three-View Consistency Momentum Contrastive Loss. Next, to mitigate the oscillations and slow convergence commonly observed in contrastive learning, we construct a dynamic contrastive loss function that adapts in real time over the training process. Finally, we validated the superiority of our model on two medical image datasets and one natural image dataset, where its classification ac-curacy and convergence speed significantly out-performed existing state-of-the-art contrastive models.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Global Information Compensation Network for Image Denoising

Shifei Ding
Qidong Wang
Lili Guo

In image denoising research, discriminative models have achieved impressive results which mainly owes to the powerful ability of convolutional networks in local feature extraction. However, there is still room for improvement due to insufficient utilization of global information. Although using fully connected layers or increasing network depth can supplement global information, this results in a significant increase in parameters and computational cost. To address these issues, we propose a global information compensation network (GICN) for image denoising in this paper. Firstly, at the shallow network part, we propose a global feature mining block that enhances the network's ability to extract global information by combining non-local blocks and the Fourier transform while improving the interpretability of the model. Secondly, between the encoder and decoder, we propose a cross-scale feature aggregation block to fuse information at different scales. Finally, we employ attention blocks to improve skip connections to better capture long-distance dependencies. Extensive experimental results show that our proposed GICN effectively compensates for global information, achieves a balance between denoising efficiency and effect, and surpasses mainstream methods in multiple benchmark tests.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

L2DGCN: Learnable Enhancement and Label Selection Dynamic Graph Convolutional Networks for Mitigating Degree Bias

jingxiao zhang
Shifei Ding
Jian Zhang
Lili Guo
Xuan Li

Graph Neural Networks (GNNs) are powerful models for node classification, but their performance is heavily reliant on manually labeled data, which is often costly and results in insufficient labeling. Recent studies have shown that message-passing neural networks struggle to propagate information in low-degree nodes, negatively affecting overall performance. To address the information bias caused by degree imbalance, we propose a Learnable Enhancement and Label Selection Dynamic Graph Convolutional Network (L2DGCN). L2DGCN consists of a teacher model and a student model. The teacher model employs an improved label propagation mechanism that enables remote label information dissemination among all nodes. The student model introduces a dynamically learnable graph enhancement strategy, perturbing edges to facilitate information exchange among low-degree nodes. This approach maintains the global graph structure while learning graph representations. Additionally, we have designed a label selector to mitigate the impact of unreliable pseudo-labels on model learning. To validate the effectiveness of our proposed model with limited labeled data, we conducted comprehensive evaluations of semi-supervised node classification across various scenarios with a limited number of annotated nodes. Experimental results demonstrate that our data enhancement model significantly contributes to node classification tasks under sparse labeling conditions.

PDF Details

IJCAI Conference 2025 Conference Paper

Multi-Agent Communication with Information Preserving Graph Contrastive Learning

Wei Du
Shifei Ding
Wei Guo
Yuqing Sun
Guoxian Yu
Lizhen Cui

Recent research in cooperative Multi-Agent Reinforcement Learning (MARL) has shown significant interest in utilizing Graph Neural Networks (GNNs) for communication learning due to their strong ability to process feature and topological information of agents into message representations for downstream action selection and coordination. However, GNNs generally assume network homogeneity that nodes of the same class tend to be interconnected. In real-world multi-agent systems, such assumptions are often unrealistic, as agents within the same class can be distant from each other. Furthermore, GNN-based MARL methods overlook the crucial role of feature similarity of agents in action coordination, which also restricts their performance. To overcome these limitations, we propose a Multi-Agent communication mechanism with Information preserving graph contrastive Learning (MAIL), which enhances message representation by preserving the comprehensive features of adjacent agents while integrating topological information. Specifically, MAIL considers three distinct graph views: original view, agent feature view, and global topological view. MAIL performs contrastive learning across three views to extract comprehensive information. MAIL effectively learns robust and expressive message representations for downstream tasks. Extensive experiments across various environments demonstrate that MAIL outperforms existing GNN-based MARL methods.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Multi-modal Anchor Gated Transformer with Knowledge Distillation for Emotion Recognition in Conversation

Jie Li
Shifei Ding
Lili Guo
Xuan Li

Emotion Recognition in Conversation (ERC) aims to detect the emotions of individual utterances within a conversation. Generating efficient and modality-specific representations for each utterance remains a significant challenge. Previous studies have proposed various models to integrate features extracted using different modality-specific encoders. However, they neglect the varying contributions of modalities to this task and introduce high complexity by aligning modalities at the frame level. To address these challenges, we propose the Multi-modal Anchor Gated Transformer with Knowledge Distillation (MAGTKD) for the ERC task. Specifically, prompt learning is employed to enhance textual modality representations, while knowledge distillation is utilized to strengthen representations of weaker modalities. Furthermore, we introduce a multi-modal anchor gated transformer to effectively integrate utterance-level representations across modalities. Extensive experiments on the IEMOCAP and MELD datasets demonstrate the effectiveness of knowledge distillation in enhancing modality representations and achieve state-of-the-art performance in emotion recognition. Our code is available at: https: //github. com/JieLi-dd/MAGTKD.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Expressive Multi-Agent Communication via Identity-Aware Learning

Wei Du
Shifei Ding
Lili Guo
Jian Zhang
Ling Ding

Information sharing through communication is essential for tackling complex multi-agent reinforcement learning tasks. Many existing multi-agent communication protocols can be viewed as instances of message passing graph neural networks (GNNs). However, due to the significantly limited expressive ability of the standard GNN method, the agent feature representations remain similar and indistinguishable even though the agents have different neighborhood structures. This further results in the homogenization of agent behaviors and reduces the capability to solve tasks effectively. In this paper, we propose a multi-agent communication protocol via identity-aware learning (IDEAL), which explicitly enhances the distinguishability of agent feature representations to break the diversity bottleneck. Specifically, IDEAL extends existing multi-agent communication protocols by inductively considering the agents' identities during the message passing process. To obtain expressive feature representations for a given agent, IDEAL first extracts the ego network centered around that agent and then performs multiple rounds of heterogeneous message passing, where different parameter sets are applied to the central agent and the other surrounding agents within the ego network. IDEAL fosters expressive communication between agents and generates distinguishable feature representations, which promotes action diversity and individuality emergence. Experimental results on various benchmarks demonstrate IDEAL can be flexibly integrated into various multi-agent communication methods and enhances the corresponding performance.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Learning Efficient and Robust Multi-Agent Communication via Graph Information Bottleneck

Shifei Ding
Wei Du
Ling Ding
Lili Guo
Jian Zhang

Efficient communication learning among agents has been shown crucial for cooperative multi-agent reinforcement learning (MARL), as it can promote the action coordination of agents and ultimately improve performance. Graph neural network (GNN) provide a general paradigm for communication learning, which consider agents and communication channels as nodes and edges in a graph, with the action selection corresponding to node labeling. Under such paradigm, an agent aggregates information from neighbor agents, which can reduce uncertainty in local decision-making and induce implicit action coordination. However, this communication paradigm is vulnerable to adversarial attacks and noise, and how to learn robust and efficient communication under perturbations has largely not been studied. To this end, this paper introduces a novel Multi-Agent communication mechanism via Graph Information bottleneck (MAGI), which can optimally balance the robustness and expressiveness of the message representation learned by agents. This communication mechanism is aim at learning the minimal sufficient message representation for an agent by maximizing the mutual information (MI) between the message representation and the selected action, and simultaneously constraining the MI between the message representation and the agent feature. Empirical results demonstrate that MAGI is more robust and efficient than state-of-the-art GNN-based MARL methods.

PDF Details DOI

EAAI Journal 2019 Journal Article

A hybrid optimization algorithm based on cuckoo search and differential evolution for solving constrained engineering problems

Zichen Zhang
Shifei Ding
Weikuan Jia

Based on Cuckoo Search (CS) and Differential Evolution (DE), a novel hybrid optimization algorithm, called CSDE, is proposed in this paper to solve constrained engineering problems. CS has strong ability on global search and less control parameters, but easy to suffer from premature convergence and lower the density of population. DE specializes in local search and good robustness, however, its convergence rate is too late to find the satisfied solution. Furthermore, these two algorithms are both proved to be especially suitable for engineering problems. This work divides population into two subgroups and adopts CS and DE for these two subgroups independently. By division, these two subgroups can exchange useful information and these two algorithms can utilize each other’s advantages to complement their shortcoming, thus avoid premature convergence, balance the quality of solution and the computation consumption, and find satisfactory global optima. Due to the tremendous design variables and constrained conditions of engineering problems, single optimizer failed to meet the requirement of precision, so hybrid optimization algorithms (such like CSDE) is the most promising mean to complete this job. Simulation results reveal that CSDE has more ability to find promising results than other 12 algorithms (including traditional algorithms and state-of-the-art algorithm) on 30 unconstrained benchmark functions, 10 constrained benchmark functions and 6 constrained engineering problems.

Details DOI

EAAI Journal 2019 Journal Article

The multi-tag semantic correlation used for micro-blog user interest modeling

Yanru Wang
Shifei Ding
Xiao Xu
Weikuan Jia

Tags play an important role in expressing the interests and attributes of microblog users, but the implicit semantic meaning of user tags is often ignored. We propose an improved micro-blog user interest modeling approach based on multi-tag semantic correlation via analyzing tag relationship and the limitations of the existing micro-blog user interest models. Firstly, the co-occurrence frequency of tag pair is calculated from the micro-blog user collection to obtain the intra-correlation between tag pair, the path is constructed based on the linking tags for each tag pair and the inter-correlation of tag pair is obtained via the shared entropy. Secondly, usertags are clustered and representative tags are obtained according to the similarity between tags, to construct the tags-representative tags matrix. Finally, we combine the above two correlations to acquire the semantic correlation matrix, based on which the users-tags matrix can be updated, thus the micro-blog user interest model based on multi-tag semantic correlation can be obtained. We evaluate our method through a series of experiments based on a dataset crawled from the open API and the results are analyzed. The results show that the interest expression model of microblog users proposed in this paper can better represent the interest characteristics of users.

Details DOI