Author name cluster

Maolin Wang

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.

6 papers

1 author row

AAAI Conference 2026 Conference Paper

Renormalization Group Guided Tensor Network Structure Search

Maolin Wang
Bowen Yu
Sheng Zhang
Linjie Mi
Wanyu Wang
Yiqi Wang
Pengyue Jia
Xuetao Wei

Tensor network structure search (TN-SS) aims to automatically discover optimal network topologies and rank configurations for efficient tensor decomposition in high-dimensional data representation. Despite recent advances, existing TN-SS methods face significant limitations in computational tractability, structure adaptivity, and optimization robustness across diverse tensor characteristics. They struggle with three key challenges: single-scale optimization missing multi-scale structures, discrete search spaces hindering smooth structure evolution, and separated structure-parameter optimization causing computational inefficiency. We propose RGTN (Renormalization Group guided Tensor Network search), a physics-inspired framework transforming TN-SS via multi-scale renormalization group flows. Unlike fixed-scale discrete search methods, RGTN uses dynamic scale-transformation for continuous structure evolution across resolutions. Its core innovation includes learnable edge gates for optimization-stage topology modification and intelligent proposals based on physical quantities like node tension measuring local stress, and edge information flow quantifying connectivity importance. Starting from low-complexity coarse scales and refining to finer ones, RGTN finds compact structures while escaping local minima via scale-induced perturbations. Extensive experiments on light field data, high-order synthetic tensors, and video completion tasks show RGTN achieves state-of-the-art compression ratios and runs 4-600 times faster than existing methods, validating the effectiveness of our physics-inspired approach.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

DANCE: Resource-Efficient Neural Architecture Search with Data-Aware and Continuous Adaptation

Maolin Wang
Tianshuo Wei
Sheng Zhang
Ruocheng Guo
Wangyu Wang
Shanshan Ye
Lixin Zou
Xuetao Wei

Neural Architecture Search (NAS) has emerged as a powerful approach for automating neural network design. However, existing NAS methods face critical limitations in real-world deployments: architectures lack adaptability across scenarios, each deployment context requires costly separate searches, and performance consistency across diverse platforms remains challenging. We propose DANCE (Dynamic Architectures with Neural Continuous Evolution), which reformulates architecture search as a continuous evolution problem through learning distributions over architectural components. DANCE introduces three key innovations: a continuous architecture distribution enabling smooth adaptation, a unified architecture space with learned selection gates for efficient sampling, and a multi-stage training strategy for effective deployment optimization. Extensive experiments across five datasets demonstrate DANCE's effectiveness. Our method consistently outperforms state-of-the-art NAS approaches in terms of accuracy while significantly reducing search costs. Under varying computational constraints, DANCE maintains robust performance while smoothly adapting architectures to different hardware requirements. The code and appendix can be found at https: //github. com/Applied-Machine-Learning-Lab/DANCE.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning

Xiao Han
ZIMO ZHAO
Wanyu Wang
Maolin Wang
Zitao Liu
Yi Chang
Xiangyu Zhao

Recent advancements in Large Language Models (LLMs) have emphasized the critical role of fine-tuning (FT) techniques in adapting LLMs to specific tasks, especially when retraining from scratch is computationally infeasible. Fine-tuning enables LLMs to leverage task- or domain-specific data, producing models that more effectively meet the requirements of targeted applications. However, conventional FT approaches often suffer from catastrophic forgetting and suboptimal data efficiency, limiting their real-world applicability. To address these challenges, this paper proposes DEAL, a novel framework that integrates Low-Rank Adaptation (LoRA) with a continuous fine-tuning strategy. By incorporating knowledge retention and adaptive parameter update modules, the framework mitigates the limitations of existing FT methods while maintaining efficiency. Experiments on 15 diverse datasets show that DEAL consistently outperforms baseline methods, yielding substantial gains in task accuracy and resource efficiency. These findings demonstrate the potential of our approach to advance continual adaptation in LLMs by enhancing task performance while improving resource efficiency. The source code is publicly available at https: //github. com/Applied-Machine-Learning-Lab/DEAL.

PDF Details

EAAI Journal 2025 Journal Article

MVIFSA: Enhancing relation detection in knowledge base question answering through multi-view information fusion and self-attention

Guoxiang Tong
Maolin Wang
Qi Hu

In the domain of knowledge base question answering systems, relation detection plays a pivotal role in interpreting entities and their intricate networks. Traditional relation detection approaches model primarily from a question and relation-level perspective without taking full advantage of word-by-word relation representations. Existing hierarchical relation detection models typically use a unidirectional, layer-specific learning manner that ignores training losses across layers. They do not take into account the critical fraction of feature vectors from the input questions and relations. Towards this, we propose MVIFSA, a multi-view information fusion model based on self-attention for relation matching. Our approach employs a multi-view relational embedding strategy, which increases the word-by-word relational embedding dimension to capture the correlations between questions and relations more efficiently. The residual learning layer is designed to reduce training loss and avoid local optimum. This is achieved by constructing residual connections between the output of the information fusion layer and the complex relation representation layer. In addition, the introduction of the self-attention mechanism allows the model to selectively pay attention to the vectors of input questions and relations, thus improving its ability to align questions with the corresponding relations. Experimental results show that MVIFSA outperforms state-of-the-art methods on benchmark datasets such as SimpleQuestions, WebQuestionsSP, and PathQuestionLarge.

Details DOI

AAAI Conference 2025 Conference Paper

SIGMA: Selective Gated Mamba for Sequential Recommendation

Ziwei Liu
Qidong Liu
Yejing Wang
Wanyu Wang
Pengyue Jia
Maolin Wang
Zitao Liu
Yi Chang

Sequential Recommender Systems (SRS) has stood out as a highly promising technique in numerous domains due to its impressive capability of capturing complex user preferences. Current SRS have employed transformer-based models to give the next-item prediction. Nevertheless, its quadratic computational complexity has often resulted in notable inefficiencies, posing a significant obstacle to real-time recommendation processes. Recently, Mamba has demonstrated its exceptional effectiveness in time series prediction, delivering substantial improvements in both efficiency and effectiveness. However, directly applying Mamba to SRS poses certain challenges. Its unidirectional structure may impede the ability to capture contextual information in user-item interactions, while its instability in state estimation may hinder the ability to capture short-term patterns in interaction sequences. To address these issues, we propose a novel framework called Selective Gated Mamba for Sequential Recommendation (SIGMA). By introducing the Partially Flipped Mamba (PF-Mamba), we construct a special bi-directional structure to address the context modeling challenge. Then, to consolidate PF-Mamba's performance, we employed an input-dependent Dense Selective Gate (DS Gate) to allocate the weights of the two directions and further filter the sequential information. Moreover, for short sequence modeling, we devise a Feature Extract GRU (FE-GRU) to capture the short-term dependencies. Experimental results demonstrate that SIGMA significantly outperforms existing baselines across five real-world datasets. Our implementation code is available in Supplementary Material to ease reproducibility.

PDF Details DOI

AAAI Conference 2019 Conference Paper

Compressing Recurrent Neural Networks with Tensor Ring for Action Recognition

Yu Pan
Jing Xu
Maolin Wang
Jinmian Ye
Fei Wang
Kun Bai
Zenglin Xu

Recurrent Neural Networks (RNNs) and their variants, such as Long-Short Term Memory (LSTM) networks, and Gated Recurrent Unit (GRU) networks, have achieved promising performance in sequential data modeling. The hidden layers in RNNs can be regarded as the memory units, which are helpful in storing information in sequential contexts. However, when dealing with high dimensional input data, such as video and text, the input-to-hidden linear transformation in RNNs brings high memory usage and huge computational cost. This makes the training of RNNs very difficult. To address this challenge, we propose a novel compact LSTM model, named as TR-LSTM, by utilizing the low-rank tensor ring decomposition (TRD) to reformulate the input-to-hidden transformation. Compared with other tensor decomposition methods, TR-LSTM is more stable. In addition, TR-LSTM can complete an end-to-end training and also provide a fundamental building block for RNNs in handling large input data. Experiments on real-world action recognition datasets have demonstrated the promising performance of the proposed TR-LSTM compared with the tensor-train LSTM and other state-of-the-art competitors.

PDF Details