Author name cluster

Shou-De Lin

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.

23 papers

2 author rows

AAAI Conference 2025 Conference Paper

Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Prompting

Yun-Da Tsai
Ting-Yu Yen
Keng-Te Liao
Shou-De Lin

Converting different modalities into generalized text, which then serves as input prompts for large language models (LLMs), is a common approach for aligning multimodal models, particularly when pairwise data is limited. Text-centric alignment method leverages the unique properties of text as a modality space, transforming diverse inputs into a unified textual representation, thereby enabling downstream models to effectively interpret various modal inputs. This study evaluates the quality and robustness of multimodal representations in the face of noise imperfections, dynamic input order permutations, and missing modalities, revealing that current text-centric alignment methods can compromise downstream robustness. To address this issue, we propose a new text-centric adversarial training approach that significantly enhances robustness compared to traditional robust training methods and pre-trained multimodal foundation models. Our findings underscore the potential of this approach to improve the robustness and adaptability of multimodal representations, offering a promising solution for dynamic and real-world applications.

PDF Details DOI

TIST Journal 2025 Journal Article

Learning on Missing Tabular Data: Attention with Self-Supervision, Not Imputation, is All You Need

Li-Wei Chang
Cheng-Te Li
Chun-Pai Yang
Shou-De Lin

Learning from data with missing values is a common challenge in real-world applications. Existing approaches for handling data incompleteness often involve imputation, which can introduce errors that propagate into downstream tasks or impose assumptions that limit the support for heterogeneous feature types. To address these issues, we propose Missing Feature Attention Network ( MFAN ), an end-to-end label prediction model that directly consumes incomplete data without requiring imputation. MFAN flexibly accommodates both continuous and categorical features through learnable embeddings, and leverages a transformer encoder with self-attention to capture the correlation among features as well as the correlation between features and missingness. This attention-based mechanism allows missing features to benefit from relationships learned among observed features, leading to enhanced hidden representations and robust prediction performance. Additionally, we introduce auxiliary self-supervised pre-training tasks that further guide the attention mechanism in modeling missingness. Experimental results on eight regression and seven classification datasets demonstrate MFAN ’s superiority over state-of-the-art end-to-end methods and imputation-based approaches. Comprehensive ablation studies confirm the effectiveness of each MFAN component, underscoring the importance of explicitly modeling correlations among observed and missing features.

Details DOI

TIST Journal 2024 Journal Article

Incremental Data Drifting: Evaluation Metrics, Data Generation, and Approach Comparison

Yu-Tung Pai
Nien-En Sun
Cheng-Te Li
Shou-De Lin

Incremental data drifting is a common problem when employing a machine-learning model in industrial applications. The underlying data distribution evolves gradually, e.g., users change their buying preferences on an E-commerce website over time. The problem needs to be addressed to obtain high performance. Right now, studies regarding incremental data drifting suffer from several issues. For one thing, there is a lack of clear-defined incremental drift datasets for examination. Existing efforts use either collected real datasets or synthetic datasets that show two obvious limitations. One is in particular when and of which type of drifts the distribution undergoes is unknown, and the other is that a simple synthesized dataset cannot reflect the complex representation we would normally face in the real world. For another, there lacks a well-defined protocol to evaluate a learner’s knowledge transfer capability on an incremental drift dataset. To provide a holistic discussion on these issues, we create approaches to generate datasets with specific drift types, and define a novel protocol for evaluation. Besides, we investigate recent advances in the transfer learning field, including Domain Adaptation and Lifelong Learning, and examine how they perform in the presence of incremental data drifting. The results unfold the relationships among drift types, knowledge preservation, and learning approaches.

Details DOI

AAAI Conference 2024 Conference Paper

Toward More Generalized Malicious URL Detection Models

Yun-Da Tsai
Cayon Liow
Yin Sheng Siang
Shou-De Lin

This paper reveals a data bias issue that can profoundly hinder the performance of machine learning models in malicious URL detection. We describe how such bias can be diagnosed using interpretable machine learning techniques and further argue that such biases naturally exist in the real world security data for training a classification model. To counteract these challenges, we propose a debiased training strategy that can be applied to most deep-learning based models to alleviate the negative effects of the biased features. The solution is based on the technique of adversarial training to train deep neural networks learning invariant embedding from biased data. Through extensive experimentation, we substantiate that our innovative strategy fosters superior generalization capabilities across both CNN-based and RNN-based detection models. The findings presented in this work not only expose a latent issue in the field but also provide an actionable remedy, marking a significant step forward in the pursuit of more reliable and robust malicious URL detection.

PDF Details DOI

TIST Journal 2023 Journal Article

Learning Privacy-Preserving Embeddings for Image Data to Be Published

Chu-Chen Li
Cheng-Te Li
Shou-De Lin

Deep learning shows superiority in learning feature representations that offer promising performance in various application domains. Recent advances have shown that privacy attributes of users and patients (e.g., identity, gender, and race) can be accurately inferred from image data. To avoid the risk of privacy leaking, data owners can resort to releasing the embeddings rather than the original images. In this article, we aim at learning to generate privacy-preserving embeddings from image data. The obtained embeddings are required to maintain the data utility (e.g., keeping the performance of the main task, such as disease prediction) and to simultaneously prevent the private attributes of data instances from being accurately inferred. We also want the hard embeddings to be successfully used to reconstruct the original images. We propose a hybrid method based on multi-task learning to reach the goal. The key idea is twofold. One is to learn the feature encoder that can benefit the main task and fool the sensitive task at the same time via iterative training and feature disentanglement. The other is to incorporate the learning of adversarial examples to mislead the sensitive attribute classification’s performance. Experiments conducted on Multi-Attribute Facial Landmark (MAFL) and NIH Chest X-ray datasets exhibit the effectiveness of our hybrid method. A set of advanced studies also shows the usefulness of each model component, the difficulty in data reconstruction, and the performance impact of task correlation.

Details DOI

NeurIPS Conference 2022 Conference Paper

Environment Diversification with Multi-head Neural Network for Invariant Learning

Bo-Wei Huang
Keng-Te Liao
Chang-Sheng Kao
Shou-De Lin

Neural networks are often trained with empirical risk minimization; however, it has been shown that a shift between training and testing distributions can cause unpredictable performance degradation. On this issue, a research direction, invariant learning, has been proposed to extract causal features insensitive to the distributional changes. This work proposes EDNIL, an invariant learning framework containing a multi-head neural network to absorb data biases. We show that this framework does not require prior knowledge about environments or strong assumptions about the pre-trained model. We also reveal that the proposed algorithm has theoretical connections to recent studies discussing properties of variant and invariant features. Finally, we demonstrate that models trained with EDNIL are empirically more robust against distributional shifts.

PDF Details

TIST Journal 2020 Journal Article

Deep Energy Factorization Model for Demographic Prediction

Chih-Te Lai
Cheng-Te Li
Shou-De Lin

Demographic information is important for various commercial and academic proposes, but in reality, few of these data are accessible for analysis and research. To solve this problem, several studies predict demographic attributes from users’ behavioral data. However, previous works suffer from different kinds of disadvantages. Handling data sparseness and defining useful features remain especially challenge tasks. In this article, we propose a novel Deep Energy Factorization Model to address these two drawbacks. The model is a designed network that performs multi-label classification and feature representation. Experiments are conducted on four datasets with four evaluation metrics. The empirical results show that our Deep Energy Factorization Model significantly outperforms state-of-the-art models.

Details DOI

AAMAS Conference 2019 Conference Paper

A Regulation Enforcement Solution for Multi-agent Reinforcement Learning

Fan-Yun Sun
Yen-Yu Chang
Yueh-Hua Wu
Shou-De Lin

Human behaviors are regularized by a variety of norms or regulations, either to maintain orders or to enhance social welfare. However, if artificially intelligent (AI) agents make decisions on behalf of human beings, it is possible that an AI agent can opt to disobey the regulations (being defective) for self-interests. In this paper, we aim to answer the following question: In a decentralized environment (no centralized authority can control agents), given that not all agents are compliant to regulations at first, can we develop a mechanism such that it is in the self-interest of non-compliant agents to comply after all. We first introduce the problem as Regulation Enforcement and formulate it using reinforcement learning and game theory. Then we propose our solution based on the key idea that although we could not alter how defective agents choose to behave, we can, however, leverage the aggregated power of compliant agents to boycott the defective ones. We conducted simulated experiments on two scenarios: Replenishing Resource Management Dilemma and Diminishing Reward Shaping Enforcement, using deep multi-agent reinforcement learning algorithms. We further use empirical game-theoretic analysis to show that the method alters the resulting empirical payoff matrices in a way that promotes compliance (making mutual compliant a Nash Equilibrium).

PDF

ICML Conference 2019 Conference Paper

MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement

Szu-Wei Fu
Chien-Feng Liao
Yu Tsao 0001
Shou-De Lin

Adversarial loss in a conditional generative adversarial network (GAN) is not designed to directly optimize evaluation metrics of a target task, and thus, may not always guide the generator in a GAN to generate data with improved metric scores. To overcome this issue, we propose a novel MetricGAN approach with an aim to optimize the generator with respect to one or multiple evaluation metrics. Moreover, based on MetricGAN, the metric scores of the generated data can also be arbitrarily specified by users. We tested the proposed MetricGAN on a speech enhancement task, which is particularly suitable to verify the proposed approach because there are multiple metrics measuring different aspects of speech signals. Moreover, these metrics are generally complex and could not be fully optimized by Lp or conventional adversarial losses.

Details

AAAI Conference 2018 Conference Paper

A Low-Cost Ethics Shaping Approach for Designing Reinforcement Learning Agents

Yueh-Hua Wu
Shou-De Lin

This paper proposes a low-cost, easily realizable strategy to equip a reinforcement learning (RL) agent the capability of behaving ethically. Our model allows the designers of RL agents to solely focus on the task to achieve, without having to worry about the implementation of multiple trivial ethical patterns to follow. Based on the assumption that the majority of human behavior, regardless which goals they are achieving, is ethical, our design integrates human policy with the RL policy to achieve the target objective with less chance of violating the ethical code that human beings normally obey.

PDF Details

NeurIPS Conference 2018 Conference Paper

MixLasso: Generalized Mixed Regression via Convex Atomic-Norm Regularization

Ian En-Hsu Yen
Wei-Cheng Lee
Kai Zhong
Sung-En Chang
Pradeep Ravikumar
Shou-De Lin

We consider a generalization of mixed regression where the response is an additive combination of several mixture components. Standard mixed regression is a special case where each response is generated from exactly one component. Typical approaches to the mixture regression problem employ local search methods such as Expectation Maximization (EM) that are prone to spurious local optima. On the other hand, a number of recent theoretically-motivated \emph{Tensor-based methods} either have high sample complexity, or require the knowledge of the input distribution, which is not available in most of practical situations. In this work, we study a novel convex estimator \emph{MixLasso} for the estimation of generalized mixed regression, based on an atomic norm specifically constructed to regularize the number of mixture components. Our algorithm gives a risk bound that trades off between prediction accuracy and model sparsity without imposing stringent assumptions on the input/output distribution, and can be easily adapted to the case of non-linear functions. In our numerical experiments on mixtures of linear as well as nonlinear regressions, the proposed method yields high-quality solutions in a wider range of settings than existing approaches.

PDF Details

ICML Conference 2017 Conference Paper

Latent Feature Lasso

Ian En-Hsu Yen
Wei-Cheng Lee
Sung-En Chang
Arun Sai Suggala
Shou-De Lin
Pradeep Ravikumar

The latent feature model (LFM), proposed in (Griffiths \& Ghahramani, 2005), but possibly with earlier origins, is a generalization of a mixture model, where each instance is generated not from a single latent class but from a combination of latent features. Thus, each instance has an associated latent binary feature incidence vector indicating the presence or absence of a feature. Due to its combinatorial nature, inference of LFMs is considerably intractable, and accordingly, most of the attention has focused on nonparametric LFMs, with priors such as the Indian Buffet Process (IBP) on infinite binary matrices. Recent efforts to tackle this complexity either still have computational complexity that is exponential, or sample complexity that is high-order polynomial w. r. t. the number of latent features. In this paper, we address this outstanding problem of tractable estimation of LFMs via a novel atomic-norm regularization, which gives an algorithm with polynomial run-time and sample complexity without impractical assumptions on the data distribution.

Details

NeurIPS Conference 2017 Conference Paper

PRUNE: Preserving Proximity and Global Ranking for Network Embedding

Yi-An Lai
Chin-Chi Hsu
Wen Hao Chen
Mi-Yen Yeh
Shou-De Lin

We investigate an unsupervised generative approach for network embedding. A multi-task Siamese neural network structure is formulated to connect embedding vectors and our objective to preserve the global node ranking and local proximity of nodes. We provide deeper analysis to connect the proposed proximity objective to link prediction and community detection in the network. We show our model can satisfy the following design properties: scalability, asymmetry, unity and simplicity. Experiment results not only verify the above design properties but also demonstrate the superior performance in learning-to-rank, classification, regression, and link prediction tasks.

PDF Details

NeurIPS Conference 2015 Conference Paper

A Dual Augmented Block Minimization Framework for Learning with Limited Memory

Ian En-Hsu Yen
Shan-Wei Lin
Shou-De Lin

In past few years, several techniques have been proposed for training of linear Support Vector Machine (SVM) in limited-memory setting, where a dual block-coordinate descent (dual-BCD) method was used to balance cost spent on I/O and computation. In this paper, we consider the more general setting of regularized \emph{Empirical Risk Minimization (ERM)} when data cannot fit into memory. In particular, we generalize the existing block minimization framework based on strong duality and \emph{Augmented Lagrangian} technique to achieve global convergence for ERM with arbitrary convex loss function and regularizer. The block minimization framework is flexible in the sense that, given a solver working under sufficient memory, one can integrate it with the framework to obtain a solver globally convergent under limited-memory condition. We conduct experiments on L1-regularized classification and regression problems to corroborate our convergence theory and compare the proposed framework to algorithms adopted from online and distributed settings, which shows superiority of the proposed approach on data of size ten times larger than the memory capacity.

PDF Details

JMLR Journal 2015 Journal Article

Combination of Feature Engineering and Ranking Models for Paper-Author Identification in KDD Cup 2013

Chun-Liang Li
Yu-Chuan Su
Ting-Wei Lin
Cheng-Hao Tsai
Wei-Cheng Chang
Kuan-Hao Huang
Tzu-Ming Kuo
Shan-Wei Lin

This paper describes the winning solution of team National Taiwan University for track 1 of KDD Cup 2013. The track 1 in KDD Cup 2013 considers the paper-author identification problem, which is to identify whether a paper is truly written by an author. First, we conduct feature engineering to transform the various types of provided text information into 97 features. Second, we train classification and ranking models using these features. Last, we combine our individual models to boost the performance by using results on the internal validation set and the official Valid set. Some effective post-processing techniques have also been proposed. Our solution achieves 0.98259 MAP score and ranks the first place on the private leaderboard of the Test set. [abs] [ pdf ][ bib ] &copy JMLR 2015. ( edit, beta )

PDF Details

IJCAI Conference 2015 Conference Paper

Measuring and Recommending Time-Sensitive Routes from Location-based Data

Hsun-Ping Hsieh
Cheng-Te Li
Shou-De Lin

Location-based services allow users to perform geo-spatial recording actions, which facilitates the mining of the moving activities of human beings. This paper proposes a system, TimeRouter, to recommend time-sensitive trip routes consisting of a sequence of locations with associated time stamps based on knowledge extracted from large-scale location check-in data. We first propose a statistical route goodness measure considering: (a) the popularity of places, (b) the visiting order of places, (c) the proper visiting time of each place, and (d) the proper transit time from one place to another. Then we construct the time-sensitive route recommender with two major functions: (1) constructing the route based on the user-specified source location with the starting time, (2) composing the route between the specified source location and the destination location given a starting time. We devise a search method, Guidance Search, to derive the routes efficiently and effectively. Experiments on Gowalla check-in datasets with user study show the promising performance of our proposed route recommendation method. 1

PDF Details

JMLR Journal 2014 Journal Article

Effective String Processing and Matching for Author Disambiguation

Wei-Sheng Chin
Yong Zhuang
Yu-Chin Juan
Felix Wu
Hsiao-Yu Tung
Tong Yu
Jui-Pin Wang
Cheng-Xia Chang

Track 2 of KDD Cup 2013 aims at determining duplicated authors in a data set from Microsoft Academic Search. This type of problems appears in many large-scale applications that compile information from different sources. This paper describes our solution developed at National Taiwan University to win the first prize of the competition. We propose an effective name matching framework and realize two implementations. An important strategy in our approach is to consider Chinese and non-Chinese names separately because of their different naming conventions. Post-processing including merging results of two predictions further boosts the performance. Our approach achieves F1-score 0.99202 on the private leader board, while 0.99195 on the public leader board. [abs] [ pdf ][ bib ] &copy JMLR 2014. ( edit, beta )

PDF Details

TIST Journal 2014 Journal Article

Measuring and Recommending Time-Sensitive Routes from Location-Based Data

Hsun-Ping Hsieh
Cheng-Te Li
Shou-De Lin

Location-based services allow users to perform geospatial recording actions, which facilitates the mining of the moving activities of human beings. This article proposes to recommend time-sensitive trip routes consisting of a sequence of locations with associated timestamps based on knowledge extracted from large-scale timestamped location sequence data (e.g., check-ins and GPS traces). We argue that a good route should consider (a) the popularity of places, (b) the visiting order of places, (c) the proper visiting time of each place, and (d) the proper transit time from one place to another. By devising a statistical model, we integrate these four factors into a route goodness function that aims to measure the quality of a route. Equipped with the route goodness, we recommend time-sensitive routes for two scenarios. The first is about constructing the route based on the user-specified source location with the starting time. The second is about composing the route between the specified source location and the destination location given a starting time. To handle these queries, we propose a search method, Guidance Search, which consists of a novel heuristic satisfaction function that guides the search toward the destination location and a backward checking mechanism to boost the effectiveness of the constructed route. Experiments on the Gowalla check-in datasets demonstrate the effectiveness of our model on detecting real routes and performing cloze test of routes, comparing with other baseline methods. We also develop a system TripRouter as a real-time demo platform.

Details DOI

ICML Conference 2014 Conference Paper

Robust Inverse Covariance Estimation under Noisy Measurements

Jun-Kun Wang
Shou-De Lin

This paper proposes a robust method to estimate the inverse covariance under noisy measurements. The method is based on the estimation of each column in the inverse covariance matrix independently via robust regression, which enables parallelization. Different from previous linear programming based methods that cannot guarantee a positive semi-definite covariance matrix, our method adjusts the learned matrix to satisfy this condition, which further facilitates the tasks of forecasting future values. Experiments on time series prediction and classification under noisy condition demonstrate the effectiveness of the approach.

Details

NeurIPS Conference 2014 Conference Paper

Sparse Random Feature Algorithm as Coordinate Descent in Hilbert Space

Ian En-Hsu Yen
Ting-Wei Lin
Shou-De Lin
Pradeep Ravikumar
Inderjit Dhillon

In this paper, we propose a Sparse Random Feature algorithm, which learns a sparse non-linear predictor by minimizing an $\ell_1$-regularized objective function over the Hilbert Space induced from kernel function. By interpreting the algorithm as Randomized Coordinate Descent in the infinite-dimensional space, we show the proposed approach converges to a solution comparable within $\eps$-precision to exact kernel method by drawing $O(1/\eps)$ number of random features, contrasted to the $O(1/\eps^2)$-type convergence achieved by Monte-Carlo analysis in current Random Feature literature. In our experiments, the Sparse Random Feature algorithm obtains sparse solution that requires less memory and prediction time while maintains comparable performance on tasks of regression and classification. In the meantime, as an approximate solver for infinite-dimensional $\ell_1$-regularized problem, the randomized approach converges to better solution than Boosting approach when the greedy step of Boosting cannot be performed exactly.

PDF Details

TIST Journal 2013 Journal Article

A modified random walk framework for handling negative ratings and generating explanations

Yu-Chih Chen
Yu-Shi Lin
Yu-Chun Shen
Shou-De Lin

The concept of random walk (RW) has been widely applied in the design of recommendation systems. RW-based approaches are effective in handling locality problem and taking extra information, such as the relationships between items or users, into consideration. However, the traditional RW-based approach has a serious limitation in handling bidirectional opinions. The propagation of positive and negative information simultaneously in a graph is nontrivial using random walk. To address the problem, this article presents a novel and efficient RW-based model that can handle both positive and negative comments with the guarantee of convergence. Furthermore, we argue that a good recommendation system should provide users not only a list of recommended items but also reasonable explanations for the decisions. Therefore, we propose a technique that generates explanations by backtracking the influential paths and subgraphs. The results of experiments on the MovieLens and Netflix datasets show that our model significantly outperforms state-of-the-art RW-based algorithms, and is capable of improving the overall performance in the ensemble with other models.

Details DOI

IJCAI Conference 2013 Conference Paper

i, Poet: Automatic Chinese Poetry Composition through a Generative Summarization Framework under Constrained Optimization

Rui Yan
Han Jiang
Mirella Lapata
Shou-De Lin
Xueqiang Lv
Xiaoming Li

Part of the long lasting cultural heritage of China is the classical ancient Chinese poems which follow strict formats and complicated linguistic rules. Automatic Chinese poetry composition by programs is considered as a challenging problem in computational linguistics and requires high Artificial Intelligence assistance, and has not been well addressed. In this paper, we formulate the poetry composition task as an optimization problem based on a generative summarization framework under several constraints. Given the user specified writing intents, the system retrieves candidate terms out of a large poem corpus, and then orders these terms to fit into poetry formats, satisfying tonal and rhythm requirements. The optimization process under constraints is conducted via iterative term substitutions till convergence, and outputs the subset with the highest utility as the generated poem. For experiments, we perform generation on large datasets of 61, 960 classic poems from Tang and Song Dynasty of China. A comprehensive evaluation, using both human judgments and ROUGE scores, has demonstrated the effectiveness of our proposed approach.

PDF Details DOI

AAAI Conference 2004 Short Paper

Interesting Instance Discovery in Multi-Relational Data

Shou-De Lin

Thegeneral area of machine discovery focuses on methods to use computers to perform or assist discovery tasks. Herbert Simon described it as "gradual problemsolving processes of searching large problem spaces for incompletely defined goal objects." Today machine discovery research falls into two major categories, scientific discovery and knowledge discovery and data mining (KDD). In this paper we propose a new research direction that lies somewhere in-between these two trends: we call it interesting instance discovery (IID) which aims at discovering interesting instances in large, multi-relational datasets.

PDF Details