Author name cluster

Boyuan 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.

8 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Accelerating Feature Conformal Prediction via Taylor Approximation

Zihao Tang
Boyuan Wang
Chuan Wen
Jiaye Teng

Conformal prediction is widely adopted in uncertainty quantification, due to its post-hoc, distribution-free, and model-agnostic properties. In the realm of modern deep learning, researchers have proposed Feature Conformal Prediction (FCP), which deploys conformal prediction in a feature space, yielding reduced band lengths. However, the practical utility of FCP is limited due to the time-consuming non-linear operations required to transform confidence bands from feature space to output space. In this paper, we present Fast Feature Conformal Prediction (FFCP), a method that accelerates FCP by leveraging a first-order Taylor expansion to approximate these non-linear operations. The proposed FFCP introduces a novel non-conformity score that is both effective and efficient for real-world applications. Empirical validations showcase that FFCP performs comparably with FCP (both outperforming the vanilla version) while achieving a significant reduction in computational time by approximately 50x in both regression and classification tasks.

PDF Details

TMLR Journal 2025 Journal Article

DNR-Pruning: Sparsity-Aware Pruning via Dying Neuron Reactivation in Convolutional Neural Networks

Boyuan Wang
Richard Jiang

In this paper, we challenge the conventional view of dead neurons—neurons that cease to activate—during deep neural network training. Traditionally regarded as problematic due to their association with optimization challenges and reduced model adaptability over training epochs, dead neurons are often seen as a hindrance. However, we present a novel perspective, demonstrating that they can be effectively leveraged to enhance network sparsity. Specifically, we propose DNR-Pruning, dying neuron reactivation based sparsity-aware pruning approach for convolutional neural networks (CNNs) that exploits the behavior of individual neurons during training. Through a systematic exploration of hyperparameter configurations, we show that dying neurons can be harnessed to improve pruning algorithms. Our method dynamically monitors the occurrence of dying neurons, enabling adaptive sparsification throughout CNN training. Extensive experiments on diverse datasets demonstrate that DNR-Pruning outperforms existing sparsity-aware pruning techniques while achieving competitive results compared to state-of-the-art methods. These findings suggest that dying neurons can serve as an efficient mechanism for network compression and resource optimization in CNNs, opening new avenues for more efficient and high-performance deep learning models.

PDF Details

AAAI Conference 2025 Conference Paper

Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning

Yun Qu
Yuhang Jiang
Boyuan Wang
Yixiu Mao
Cheems Wang
Chang Liu
Xiangyang Ji

Reinforcement learning (RL) often encounters delayed and sparse feedback in real-world applications, even with only episodic rewards. Previous approaches have made some progress in reward redistribution for credit assignment but still face challenges, including training difficulties due to redundancy and ambiguous attributions stemming from overlooking the multifaceted nature of mission performance evaluation. Hopefully, Large Language Model (LLM) encompasses fruitful decision-making knowledge and provides a plausible tool for reward redistribution. Even so, deploying LLM in this case is non-trivial due to the misalignment between linguistic knowledge and the symbolic form requirement, together with inherent randomness and hallucinations in inference. To tackle these issues, we introduce LaRe, a novel LLM-empowered symbolic-based decision-making framework, to improve credit assignment. Key to LaRe is the concept of the Latent Reward, which works as a multi-dimensional performance evaluation, enabling more interpretable goal attainment from various perspectives and facilitating more effective reward redistribution. We examine that semantically generated code from LLM can bridge linguistic knowledge and symbolic latent rewards, as it is executable for symbolic objects. Meanwhile, we design latent reward self-verification to increase the stability and reliability of LLM inference. Theoretically, reward-irrelevant redundancy elimination in the latent reward benefits RL performance from more accurate reward estimation. Extensive experimental results witness that LaRe (i) achieves superior temporal credit assignment to SOTA methods, (ii) excels in allocating contributions among multiple agents, and (iii) outperforms policies trained with ground truth rewards for certain tasks.

PDF Details DOI

ICML Conference 2024 Conference Paper

LLM-Empowered State Representation for Reinforcement Learning

Boyuan Wang
Yun Qu 0002
Yuhang Jiang 0001
Jianzhun Shao
Chang Liu 0030
Wenming Yang
Xiangyang Ji

Conventional state representations in reinforcement learning often omit critical task-related details, presenting a significant challenge for value networks in establishing accurate mappings from states to task rewards. Traditional methods typically depend on extensive sample learning to enrich state representations with task-specific information, which leads to low sample efficiency and high time costs. Recently, surging knowledgeable large language models (LLM) have provided promising substitutes for prior injection with minimal human intervention. Motivated by this, we propose LLM-Empowered State Representation (LESR), a novel approach that utilizes LLM to autonomously generate task-related state representation codes which help to enhance the continuity of network mappings and facilitate efficient training. Experimental results demonstrate LESR exhibits high sample efficiency and outperforms state-of-the-art baselines by an average of 29% in accumulated reward in Mujoco tasks and 30% in success rates in Gym-Robotics tasks. Codes of LESR are accessible at https: //github. com/thu-rllab/LESR.

Details

NeurIPS Conference 2023 Conference Paper

Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks

Yun Qu
Boyuan Wang
Jianzhun Shao
Yuhang Jiang
Chen Chen
Zhenbin Ye
Liu Linc
Yang Feng

The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre-collected offline datasets that represent real-world complexities and practical applications. However, existing datasets often fall short in their simplicity and lack of realism. To address this gap, we propose Hokoff, a comprehensive set of pre-collected datasets that covers both offline RL and offline MARL, accompanied by a robust framework, to facilitate further research. This data is derived from Honor of Kings, a recognized Multiplayer Online Battle Arena (MOBA) game known for its intricate nature, closely resembling real-life situations. Utilizing this framework, we benchmark a variety of offline RL and offline MARL algorithms. We also introduce a novel baseline algorithm tailored for the inherent hierarchical action space of the game. We reveal the incompetency of current offline RL approaches in handling task complexity, generalization and multi-task learning.

PDF Details

ICLR Conference 2023 Conference Paper

In-sample Actor Critic for Offline Reinforcement Learning

Hongchang Zhang
Yixiu Mao
Boyuan Wang
Shuncheng He
Yi Xu 0008
Xiangyang Ji

Offline reinforcement learning suffers from out-of-distribution issue and extrapolation error. Most methods penalize the out-of-distribution state-action pairs or regularize the trained policy towards the behavior policy but cannot guarantee to get rid of extrapolation error. We propose In-sample Actor Critic (IAC) which utilizes sampling-importance resampling to execute in-sample policy evaluation. IAC only uses the target Q-values of the actions in the dataset to evaluate the trained policy, thus avoiding extrapolation error. The proposed method performs unbiased policy evaluation and has a lower variance than importance sampling in many cases. Empirical results show that IAC obtains competitive performance compared to the state-of-the-art methods on Gym-MuJoCo locomotion domains and much more challenging AntMaze domains.

Details

IJCAI Conference 2021 Conference Paper

Adaptive Residue-wise Profile Fusion for Low Homologous Protein Secondary Structure Prediction Using External Knowledge

Qin Wang
Jun Wei
Boyuan Wang
Zhen Li
Sheng Wang
Shuguang Cui

Protein secondary structure prediction (PSSP) is essential for protein function analysis. However, for low homologous proteins, the PSSP suffers from insufficient input features. In this paper, we explicitly import external self-supervised knowledge for low homologous PSSP under the guidance of residue-wise (amino acid wise) profile fusion. In practice, we firstly demonstrate the superiority of profile over Position-Specific Scoring Matrix (PSSM) for low homologous PSSP. Based on this observation, we introduce the novel self-supervised BERT features as the pseudo profile, which implicitly involves the residue distribution in all native discovered sequences as the complementary features. Furthermore, a novel residue-wise attention is specially designed to adaptively fuse different features (i. e. , original low-quality profile, BERT based pseudo profile), which not only takes full advantage of each feature but also avoids noise disturbance. Besides, the feature consistency loss is proposed to accelerate the model learning from multiple semantic levels. Extensive experiments confirm that our method outperforms state-of-the-arts (i. e. , 4. 7% for extremely low homologous cases on BC40 dataset).

PDF Details DOI

AAAI Conference 2021 Conference Paper

PSSM-Distil: Protein Secondary Structure Prediction (PSSP) on Low-Quality PSSM by Knowledge Distillation with Contrastive Learning

Qin Wang
Boyuan Wang
Zhenlei Xu
Jiaxiang Wu
Peilin Zhao
Zhen Li
Sheng Wang
Junzhou Huang

Protein secondary structure prediction (PSSP) is an essential task in computational biology. To achieve the accurate PSSP, the general and vital feature engineering is to use multiple sequence alignment (MSA) for Position-Specific Scoring Matrix (PSSM) extraction. However, when only low-quality PSSM can be obtained due to poor sequence homology, previous PSSP accuracy (merely around 65%) is far from practical usage for subsequent tasks. In this paper, we propose a novel PSSM-Distil framework for PSSP on low-quality PSSM, which not only enhances the PSSM feature at a lower level but also aligns the feature distribution at a higher level. In practice, the PSSM-Distil first exploits the proteins with high-quality PSSM to achieve a teacher network for PSSP in a full-supervised way. Under the guidance of the teacher network, the low-quality PSSM and corresponding student network with low discriminating capacity are effectively resolved by feature enhancement through EnhanceNet and distribution alignment through knowledge distillation with contrastive learning. Further, our PSSM-Distil supports the input from a pre-trained protein sequence language BERT model to provide auxiliary information, which is designed to address the extremely low-quality PSSM cases, i. e. , no homologous sequence. Extensive experiments demonstrate the proposed PSSM-Distil outperforms state-of-the-art models on PSSP by 6% on average and nearly 8% in extremely low-quality cases on public benchmarks, BC40 and CB513.

PDF Details