Author name cluster

Feng Guo

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.

7 papers

2 author rows

AAAI Conference 2026 Conference Paper

Beyond Superficial Forgetting: Thorough Unlearning Through Knowledge Density Estimation and Block Re-Insertion

Feng Guo
Yuntao Wen
Shen Gao
Junshuo Zhang
Shuo Shang

Machine unlearning, which selectively removes harmful knowledge from a pre-trained model without retraining from scratch, is crucial for addressing privacy, regulatory compliance, and ethical concerns in Large Language Models (LLMs). However, existing unlearning methods often struggle to thoroughly remove harmful knowledge, leaving residual harmful knowledge that can be easily recovered. To address these limitations, we propose Knowledge Density-Guided Unlearning via Blocks Reinsertion (KUnBR), a novel approach that first identifies layers with rich harmful knowledge and then thoroughly eliminates the harmful knowledge via re-insertion strategy. Our method introduces knowledge density estimation to quantify and locate layers containing the most harmful knowledge, enabling precise unlearning. Additionally, we design a layer re-insertion strategy that extracts and re-inserts harmful knowledge-rich layers into the original LLM, bypassing gradient obstruction caused by cover layers and ensuring effective gradient propagation during unlearning. Extensive experiments conducted on several unlearning and general capability benchmarks demonstrate that KUnBR achieves state-of-the-art forgetting performance while maintaining model utility.

PDF Details DOI

EAAI Journal 2026 Journal Article

Context-aware and deformation-adaptive small unmanned aerial vehicles detection via parallel attention and multi-scale fusion

Hang Yu
Jialin Bao
Yibo Sun
Suiping Zhou
Zhengfa Yu
Yilu Chen
Ke Yan
Yifan Yang

Detecting small Unmanned Aerial Vehicles (UAV) in complex environments remains a persistent challenge, primarily due to their diminutive visual scale, frequent geometric deformations, and interference from cluttered backgrounds. To address these issues, this paper presents Context-Aware and Deformation-Adaptive Small Unmanned Aerial Vehicles Detection via Parallel Attention and Multi-Scale Fusion, a compact and perception-enhanced detection framework. From the perspective of artificial intelligence, the model advances adaptive feature representation and context-aware learning through three synergistic modules: an Attention-Modulated Deformable Convolution for dynamic spatial adaptability, an Asymptotic Feature Pyramid Network for progressive multi-scale semantic fusion, and a Coordinate-Aligned Parallel Attention mechanism for refined spatial–channel discrimination. Extensive experiments conducted on the Dalian University of Technology Anti-UAV Dataset demonstrate that the proposed framework outperforms state-of-the-art detection models, achieving a precision of 97. 4%, recall of 90. 8%, F1-score of 94%, and mean Average Precision at Intersection over Union threshold equals 0. 5 of 95. 8%, while maintaining an efficient architecture that is amenable to practical deployment and real-time-capable inference.

Details DOI

EAAI Journal 2024 Journal Article

A two-stage framework for pixel-level pavement surface crack detection

Feng Guo
Jian Liu
Quanyi Xie
Huayang Yu

Surface crack is one of the most common distresses of pavement structure, impacting its serviceability and sustainability. Over the past decade, many efforts have been devoted to developing computer vision-based models (e. g. , image processing- or deep learning-based) for the automatic detection of pavement surface crack. However, there is a great gap between the public image data taken by the phone or other portable devices and the real-world image data acquired by the linear array charge-coupled device (CCD) camera, which usually is high resolution and contains limited crack pixels per image. To improve the pavement surface crack detection efficiency and accuracy in engineering practice, we propose a novel two-stage framework for automatic pavement surface detection at the pixel level. In stage I, the images concluding pixel cracks are selected using a convolutional neural network (CNN)-based classification network. In stage II, the selected images are processed with our proposed separation-combination strategy and the second version of crack transformer (CTv2) for pavement surface crack detection at the pixel level. Comprehensive experimental investigation and comparison have been conducted on training performance and visualization results, validating the superiority of the developed framework. It paves the way for the large-scale application of automatic pavement crack detection in an efficient manner.

Details DOI

ICLR Conference 2020 Conference Paper

AutoQ: Automated Kernel-Wise Neural Network Quantization

Qian Lou
Feng Guo
Minje Kim
Lantao Liu
Lei Jiang 0001

Network quantization is one of the most hardware friendly techniques to enable the deployment of convolutional neural networks (CNNs) on low-power mobile devices. Recent network quantization techniques quantize each weight kernel in a convolutional layer independently for higher inference accuracy, since the weight kernels in a layer exhibit different variances and hence have different amounts of redundancy. The quantization bitwidth or bit number (QBN) directly decides the inference accuracy, latency, energy and hardware overhead. To effectively reduce the redundancy and accelerate CNN inferences, various weight kernels should be quantized with different QBNs. However, prior works use only one QBN to quantize each convolutional layer or the entire CNN, because the design space of searching a QBN for each weight kernel is too large. The hand-crafted heuristic of the kernel-wise QBN search is so sophisticated that domain experts can obtain only sub-optimal results. It is difficult for even deep reinforcement learning (DRL) DDPG-based agents to find a kernel-wise QBN configuration that can achieve reasonable inference accuracy. In this paper, we propose a hierarchical-DRL-based kernel-wise network quantization technique, AutoQ, to automatically search a QBN for each weight kernel, and choose another QBN for each activation layer. Compared to the models quantized by the state-of-the-art DRL-based schemes, on average, the same models quantized by AutoQ reduce the inference latency by 54.06%, and decrease the inference energy consumption by 50.69%, while achieving the same inference accuracy.

Details

NeurIPS Conference 2020 Conference Paper

Reconsidering Generative Objectives For Counterfactual Reasoning

Danni Lu
Chenyang Tao
Junya Chen
Fan Li
Feng Guo
Lawrence Carin

There has been recent interest in exploring generative goals for counterfactual reasoning, such as individualized treatment effect (ITE) estimation. However, existing solutions often fail to address issues that are unique to causal inference, such as covariate balancing and (infeasible) counterfactual validation. As a step towards more flexible, scalable and accurate ITE estimation, we present a novel generative Bayesian estimation framework that integrates representation learning, adversarial matching and causal estimation. By appealing to the Robinson decomposition, we derive a reformulated variational bound that explicitly targets the causal effect estimation rather than specific predictive goals. Our procedure acknowledges the uncertainties in representation and solves a Fenchel mini-max game to resolve the representation imbalance for better counterfactual generalization, justified by new theory. Further, the latent variable formulation employed enables robustness to unobservable latent confounders, extending the scope of its applicability. The utility of the proposed solution is demonstrated via an extensive set of tests against competing solutions, both under various simulation setups and to real-world datasets, with encouraging results reported.

PDF Details

EAAI Journal 2016 Journal Article

Novel continuous function prediction model using an improved Takagi–Sugeno fuzzy rule and its application based on chaotic time series

Feng Guo
Lin Lin
Chen Wang

A novel continuous function prediction model (CFPM) is proposed to resolve prediction problem whose input and output are both continuous functions (CFs). CFPM can simplify sample space reconstruction by using the coefficients of CFs, and use an improved Takagi–Sugeno (TS) fuzzy rule to predict output CF by optimizing the tendency of input CFs. The improved TS fuzzy rule handles each input CF as a consequent parameter and can obtain the nonlinear tendency. After learning process by using opinion-leader-based particle swarm optimization, output CF is determined. In the data prediction based on chaotic time series, CF can either be obtained directly or be fitted by discrete data points, thus the prediction range is enlarged because more discrete data points can be generated once output CF is determined. Two experiments and three cases based on chaotic time series are performed to validate CFPM. The Mackey–Glass chaotic time series is used to prove CFPM validation, while the NN3 time series is used to evaluate CFPM performance. The cases on exhaust gas temperature (EGT), EGT margin and delta EGT are used to show that CFPM is valuable in health status prediction for a particular aircraft engine in the practical engineering field.

Details DOI

EAAI Journal 2015 Journal Article

Novel informative feature samples extraction model using cell nuclear pore optimization

Lin Lin
Feng Guo
Xiaolong Xie

A novel informative feature samples extraction model is proposed to approximate massive original samples (OSs) by using a small number of informative feature samples (IFSs). In this model, (1) the feature samples (FSs) are identified using Support Vector Regression and Quantum-behaved Particle Swarm Optimization and (2) the IFSs space is established based on the Cell Nuclear Pore Optimization (CNPO) algorithm. CNPO uses a pore vector containing 0 or 1 to extract the essential FSs with high contribution based on the thought of cell nuclear pore selection mechanism. This model can be used to identify the continuous parameter based on the IFSs without massive OSs and time-consuming work. Two experiments are used to validate the proposed model, and one case is used to illustrate the practical value in the real engineer field. The experiments show that the IFSs could approximately represent the massive OSs, and the case shows that the model is helpful to identify the continuous parameters for the hydraulic turbine type design.

Details DOI