Author name cluster

Kun Song

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

EAAI Journal 2025 Journal Article

An adaptive weighted stacking ensemble framework for photovoltaic power generation forecasting with joint optimization of features and hyperparameters

Shaolong Zheng
Danyun Li
Yidong Li
Zihan Zeng
Yuxuan Zhou
Changsi Li
Kun Song

Accurate photovoltaic (PV) power forecasting is crucial for the efficient operation of power systems. However, the limited availability of historical data often hinders prediction accuracy. To address this challenge, an adaptive weighted stacking (AWS) ensemble framework is proposed, combining artificial intelligence ensemble models with joint optimization (JO) of features and hyperparameters to enhance prediction performance in small sample (SS) scenarios. In the framework, a base learner selection strategy based on kernel hierarchical clustering (KHC) is used to balance model performance and diversity. Multi-initiated parallel bayesian optimization with early stopping (MI-PBOES) algorithm is employed for the JO of features and hyperparameters to obtain the optimal subset of features and the corresponding parameter configuration. Additionally, an AWS strategy is employed to dynamically adjust ensemble weights, further improving accuracy and robustness. To evaluate its effectiveness in engineering applications, experiments were conducted using data from the desert knowledge australia (DKA) solar centre. The results indicate that the proposed framework reduces root mean square error (RMSE) by 51. 84% and mean absolute error (MAE) by 56. 42% compared to traditional machine learning models, while RMSE decreases by 129. 89% and MAE by 124. 82% compared to deep learning models. Under noisy conditions, RMSE and MAE are reduced by 39. 46% and 37. 37%, respectively, showing remarkable prediction performance and robustness.

Details DOI

AAAI Conference 2025 Conference Paper

Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update

Qing Li
Jiahui Geng
Derui Zhu
Zongxiong Chen
Kun Song
Lei Ma
Fakhri Karray

Warning: This paper contains offensive content that may disturb some readers. Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the integration of images significantly shifts the model's internal activations during the forward pass, diverging from those triggered by textual input. Moreover, the safety alignments of LLMs embedded within VLMs are not sufficiently robust to handle the activations discrepancies, making the models vulnerable to even the simplest jailbreaking attacks. To address this issue, we propose an internal activation revision approach that efficiently revises activations during generation, steering the model toward safer outputs. Our framework incorporates revisions at both the layer and head levels, offering control over the model's generation at varying levels of granularity. In addition, we explore three strategies for constructing positive and negative samples and two approaches for extracting revision vectors, resulting in different variants of our method. Comprehensive experiments demonstrate that the internal activation revision method significantly improves the safety of widely used VLMs, reducing attack success rates by an average of 48.94%, 34.34%, 43.92%, and 52.98% on SafeBench, Safe-Unsafe, Unsafe, and MM-SafetyBench, respectively, while minimally impacting model helpfulness.

PDF Details DOI

IROS Conference 2025 Conference Paper

P 2 Explore: Efficient Exploration in Unknown Cluttered Environment with Floor Plan Prediction

Kun Song
Gaoming Chen
Masayoshi Tomizuka
Wei Zhan
Zhenhua Xiong 0001
Mingyu Ding

Robot exploration aims at the reconstruction of unknown environments, and it is important to achieve it with shorter paths. Traditional methods focus on optimizing the visiting order of frontiers based on current observations, which may lead to local-minimal results. Recently, by predicting the structure of the unseen environment, the exploration efficiency can be further improved. However, in a cluttered environment, due to the randomness of obstacles, the ability to predict is weak. Moreover, this inaccuracy will lead to limited improvement in exploration. Therefore, we propose FPUNet which can be efficient in predicting the layout of noisy indoor environments. Then, we extract the segmentation of rooms and construct their topological connectivity based on the predicted map. The visiting order of these predicted rooms is optimized which can provide high-level guidance for exploration. The FPUNet is compared with other network architectures which demonstrates it is the SOTA method for this task. Extensive experiments in simulations show that our method can shorten the path length by 2. 18% to 34. 60% compared to the baselines.

Details

AAAI Conference 2024 Conference Paper

Robustly Train Normalizing Flows via KL Divergence Regularization

Kun Song
Ruben Solozabal
Hao Li
Martin Takáč
Lu Ren
Fakhri Karray

In this paper, we find that the training of Normalizing Flows (NFs) are easily affected by the outliers and a small number (or high dimensionality) of training samples. To solve this problem, we propose a Kullback–Leibler (KL) divergence regularization on the Jacobian matrix of NFs. We prove that such regularization is equivalent to adding a set of samples whose covariance matrix is the identity matrix to the training set. Thus, it reduces the negative influence of the outliers and the small sample number on the estimation of the covariance matrix, simultaneously. Therefore, our regularization makes the training of NFs robust. Ultimately, we evaluate the performance of NFs on out-of-distribution (OoD) detection tasks. The excellent results obtained demonstrate the effectiveness of the proposed regularization term. For example, with the help of the proposed regularization, the OoD detection score increases at most 30% compared with the one without the regularization.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning

Kun Song
Huimin Ma
Bochao Zou
Huishuai Zhang
Weiran Huang

Due to the limited availability of data, existing few-shot learning methods trained from scratch fail to achieve satisfactory performance. In contrast, large-scale pre-trained models such as CLIP demonstrate remarkable few-shot and zero-shot capabilities. To enhance the performance of pre-trained models for downstream tasks, fine-tuning the model on downstream data is frequently necessary. However, fine-tuning the pre-trained model leads to a decrease in its generalizability in the presence of distribution shift, while the limited number of samples in few-shot learning makes the model highly susceptible to overfitting. Consequently, existing methods for fine-tuning few-shot learning primarily focus on fine-tuning the model's classification head or introducing additional structure. In this paper, we introduce a fine-tuning approach termed Feature Discrimination Alignment (FD-Align). Our method aims to bolster the model's generalizability by preserving the consistency of spurious features across the fine-tuning process. Extensive experimental results validate the efficacy of our approach for both ID and OOD tasks. Once fine-tuned, the model can seamlessly integrate with existing methods, leading to performance improvements. Our code can be found in https: //github. com/skingorz/FD-Align.

PDF Details

AAAI Conference 2017 Conference Paper

Bilateral k-Means Algorithm for Fast Co-Clustering

Junwei Han
Kun Song
Feiping Nie
Xuelong Li

With the development of the information technology, the amount of data, e. g. text, image and video, has been increased rapidly. Efﬁciently clustering those large scale data sets is a challenge. To address this problem, this paper proposes a novel co-clustering method named bilateral k-means algorithm (BKM) for fast co-clustering. Different from traditional k-means algorithms, the proposed method has two indicator matrices P and Q and a diagonal matrix S to be solved, which represent the cluster memberships of samples and features, and the co-cluster centres, respectively. Therefore, it could implement different clustering tasks on the samples and features simultaneously. We also introduce an effective approach to solve the proposed method, which involves less multiplication. The computational complexity is analyzed. Extensive experiments on various types of data sets are conducted. Compared with the state-of-the-art clustering methods, the proposed BKM not only has faster computational speed, but also achieves promising clustering results.

PDF Details

AAAI Conference 2017 Conference Paper

Parameter Free Large Margin Nearest Neighbor for Distance Metric Learning

Kun Song
Feiping Nie
Junwei Han
Xuelong Li

We introduce a novel supervised metric learning algorithm named parameter free large margin nearest neighbor (PFLMNN) which can be seen as an improvement of the classical large margin nearest neighbor (LMNN) algorithm. The contributions of our work consist of two aspects. First, our method discards the costterm which shrinks the distances between inquiry input and its k target neighbors (the k nearest neighbors with same labels as inquiry input) in LMNN, and only focuses on improving the action to push the imposters (the samples with different labels form the inquiry input) apart out of the neighborhood of inquiry. As a result, our method does not have the parameter needed to tune on the validating set, which makes it more convenient to use. Second, by leveraging the geometry information of the imposters, we construct a novel cost function to penalize the smalldistances between each inquiry and its imposters. Different from LMNN considering every imposter located in the neighborhood of each inquiry, our method only takes care of the nearest imposters. Because when the nearest imposter is pushed out of the neighborhood of its inquiry, other imposters would be all out. In this way, the constraints in our model are much less than that of LMNN, which makes our method much easier to find the optimal distance metric. Consequently, our method not only learns a better distance metric than LMNN, but also runs faster than LMNN. Extensive experiments on different data sets with various sizes and difficulties are conducted, and the results have shown that, compared with LMNN, PFLMNN achieves better classification results.

PDF Details

IJCAI Conference 2017 Conference Paper

Two dimensional Large Margin Nearest Neighbor for Matrix Classification

Kun Song
Feiping Nie
Junwei Han

Matrices are common forms of data that are encountered in a wide range of real applications. How to classify this kind of data is an important research topic. In this paper, we propose a novel distance metric learning method named two dimensional large margin nearest neighbor (2DLMNNN), for improving the performance of k nearest neighbor (KNN) classifier in matrix classification. In the proposed method, left and right projection matrices are employed to define the matrix-based Mahalanobis distance, which is used to construct the objective aimed at separating points in different classes by a large margin. The parameters in those two projection matrices are much less than that in its vector-based counterpart, thus our method reduces the risks of overfitting. We also introduce a framework for solving the proposed 2DLMNN. The convergence behavior, initialization, and parameter determination are also analyzed. Compared with vector-based methods, 2DLMNN performs better for matrix data classification. Promising experimental results on several data sets are provided to demonstrate the effectiveness of our method.

PDF Details