Deep Reinforcement Learning For Dynamic Algorithm Selection: A Proof-Of-Principle Study On Differential Evolution,
2024
Singapore Management University
Deep Reinforcement Learning For Dynamic Algorithm Selection: A Proof-Of-Principle Study On Differential Evolution, Hongshu Guo, Yining Ma, Zeyuan Ma, Jiacheng Chen, Xinglin Zhang, Zhiguang Cao, Jun Zhang, Yue-Jiao Gong
Research Collection School Of Computing and Information Systems
Evolutionary algorithms, such as differential evolution, excel in solving real-parameter optimization challenges. However, the effectiveness of a single algorithm varies across different problem instances, necessitating considerable efforts in algorithm selection or configuration. This article aims to address the limitation by leveraging the complementary strengths of a group of algorithms and dynamically scheduling them throughout the optimization progress for specific problems. We propose a deep reinforcement learning-based dynamic algorithm selection framework to accomplish this task. Our approach models the dynamic algorithm selection a Markov decision process, training an agent in a policy gradient manner to select the most suitable algorithm according …
Adaptive Content-Aware Influence Maximization Via Online Learning To Rank,
2024
Singapore Management University
Adaptive Content-Aware Influence Maximization Via Online Learning To Rank, Konstantinos Theocharidis, Panagiotis Karras, Manolis Terrovitis, Spiros Skiadopoulos, Hady Wirawan Lauw
Research Collection School Of Computing and Information Systems
How can we adapt the composition of a post over a series of rounds to make it more appealing in a social network? Techniques that progressively learn how to make a fixed post more influential over rounds have been studied in the context of the Influence Maximization (IM) problem, which seeks a set of seed users that maximize a post’s influence. However, there is no work on progressively learning how a post’s features affect its influence. In this article, we propose and study the problem of Adaptive Content-Aware Influence Maximization (ACAIM), which calls to find k features to form a …
Improving Educational Delivery And Content In Juvenile Detention Centers,
2024
Old Dominion University
Improving Educational Delivery And Content In Juvenile Detention Centers, Yomna Elmousalami
Undergraduate Research Symposium
Students in juvenile detention centers have the greatest need to receive improvements in educational delivery and content; however, they are one of the “truly disadvantaged” populations in terms of receiving those improvements. This work presents a qualitative data analysis based on a focus group meeting with stakeholders at a local Juvenile Detention Center. The current educational system in juvenile detention centers is based on paper worksheets, single-room style teaching methods, outdated technology, and a shortage of textbooks and teachers. In addition, detained students typically have behavioral challenges that are deemed "undesired" in society. As a result, many students miss classes …
Multi-Modality Transformer For E-Commerce: Inferring User Purchase Intention To Bridge The Query-Product Gap,
2024
Kennesaw State University
Multi-Modality Transformer For E-Commerce: Inferring User Purchase Intention To Bridge The Query-Product Gap, Srivatsa Mallapragada
Dissertations
The rapid growth of e-commerce has necessitated the development of sophisticated product retrieval systems that can effectively match user queries with relevant products. However, the semantic gap between queries and products remains a significant challenge, as traditional retrieval methods often fail to capture the nuances of user purchase intentions. E-commerce click-stream data and product catalogs offer critical user behavior insights and product knowledge that are untapped in the current product search algorithms. This dissertation presents learning strategies that leverage the query-product transaction logs to enrich the pipeline of our proposed multi-modal transformer model, which transforms initial user queries into pseudo …
Mechanistic Investigation Of C—C Bond Activation Of Phosphaalkynes With Pt(0) Complexes,
2024
The University of Texas Rio Grande Valley
Mechanistic Investigation Of C—C Bond Activation Of Phosphaalkynes With Pt(0) Complexes, Roberto M. Escobar, Abdurrahman C. Ateşin, Christian Müller, William D. Jones, Tülay Ateşin
Research Symposium
Carbon–carbon (C–C) bond activation has gained increased attention as a direct method for the synthesis of pharmaceuticals. Due to the thermodynamic stability and kinetic inaccessibility of the C–C bonds, however, activation of C–C bonds by homogeneous transition-metal catalysts under mild homogeneous conditions is still a challenge. Most of the systems in which the activation occurs either have aromatization or relief of ring strain as the primary driving force. The activation of unstrained C–C bonds of phosphaalkynes does not have this advantage. This study employs Density Functional Theory (DFT) calculations to elucidate Pt(0)-mediated C–CP bond activation mechanisms in phosphaalkynes. Investigating the …
The Impact Of Data Preparation And Model Complexity On The Natural Language Classification Of Chinese News Headlines,
2024
Air Force Institute of Technology
The Impact Of Data Preparation And Model Complexity On The Natural Language Classification Of Chinese News Headlines, Torrey J. Wagner, Dennis Guhl, Brent T. Langhals
Faculty Publications
Given the emergence of China as a political and economic power in the 21st century, there is increased interest in analyzing Chinese news articles to better understand developing trends in China. Because of the volume of the material, automating the categorization of Chinese-language news articles by headline text or titles can be an effective way to sort the articles into categories for efficient review. A 383,000-headline dataset labeled with 15 categories from the Toutiao website was evaluated via natural language processing to predict topic categories. The influence of six data preparation variations on the predictive accuracy of four algorithms was …
Intelligent Algorithm Safety: Concepts, Scientific Problems And Prospects,
2024
CAS Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, China
Intelligent Algorithm Safety: Concepts, Scientific Problems And Prospects, Xueqi Cheng, Wei Chen, Huawei Shen, Shiguang Shan, Xilin Chen, Guojie Li
Bulletin of Chinese Academy of Sciences (Chinese Version)
Intelligent algorithms refer to the methods embodied in the computational processes that realize intelligence. These methods are often characterized by being data-driven, involving uncertain computations, and with unexplainable model inferences. These characteristics simultaneously introduce potential safety risks to the application of intelligent algorithms and AI. This study firstly explores the concepts of intelligent algorithm safety. Specifically, intelligent algorithm safety, based on the degree of human-machine integration, extends from the univariate safety of the algorithm itself to the bivariate applicational safety when the algorithm serves humans, and finally evolves into the multivariate systemic safety arises within complex socio-technical systems of human-machine …
Wang Tilings In Arbitrary Dimensions,
2024
Oregon State University
Wang Tilings In Arbitrary Dimensions, Ian Tassin
Rose-Hulman Undergraduate Mathematics Journal
This paper makes a new observation about arbitrary dimensional Wang Tilings,
demonstrating that any d -dimensional tile set that can tile periodically along d − 1 axes must be able to tile periodically along all axes.
This work also summarizes work on Wang Tiles up to the present day, including
definitions for various aspects of Wang Tilings such as periodicity and the validity of a tiling. Additionally, we extend the familiar 2D definitions for Wang Tiles and associated properties into arbitrary dimensional spaces. While there has been previous discussion of arbitrary dimensional Wang Tiles in other works, it has been …
Sepsis Treatment: Reinforced Sequential Decision-Making For Saving Lives,
2024
Purdue University
Sepsis Treatment: Reinforced Sequential Decision-Making For Saving Lives, Dipesh Tamboli, Jiayu Chen, Kiran Pranesh Jotheeswaran, Denny Yu, Vaneet Aggarwal
Graduate Industrial Research Symposium
Sepsis, a life-threatening condition triggered by the body's exaggerated response to infection, demands urgent intervention to prevent severe complications. Existing machine learning methods for managing sepsis struggle in offline scenarios, exhibiting suboptimal performance with survival rates below 50%. Our project introduces the "PosNegDM: Reinforcement Learning with Positive and Negative Demonstrations for Sequential Decision-Making" framework utilizing an innovative transformer-based model and a feedback reinforcer to replicate expert actions while considering individual patient characteristics. A mortality classifier with 96.7% accuracy guides treatment decisions towards positive outcomes. The PosNegDM framework significantly improves patient survival, saving 97.39% of patients and outperforming established machine learning …
Online Class-Incremental Learning For Real-World Food Image Classification,
2024
Purdue University
Online Class-Incremental Learning For Real-World Food Image Classification, Siddeshwar Raghavan, Jiangpeng He, Fengqing Zhu
Graduate Industrial Research Symposium
Food image classification is essential for monitoring health and tracking dietary in image-based dietary assessment methods. However, conventional systems often rely on static datasets with fixed classes and uniform distribution. In contrast, real-world food consumption patterns, shaped by cultural, economic, and personal influences, involve dynamic and evolving data. Thus, it requires the classification system to cope with continuously evolving data. Online Class Incremental Learning (OCIL) addresses the challenge of learning continuously from a single-pass data stream while adapting to the new knowledge and reducing catastrophic forgetting. Experience Replay (ER) based OCIL methods store a small portion of previous data and …
A Machine Learning Model Of Perturb-Seq Data For Use In Space Flight Gene Expression Profile Analysis,
2024
Purdue University
A Machine Learning Model Of Perturb-Seq Data For Use In Space Flight Gene Expression Profile Analysis, Liam F. Johnson, James Casaletto, Lauren Sanders, Sylvain Costes
Graduate Industrial Research Symposium
The genetic perturbations caused by spaceflight on biological systems tend to have a system-wide effect which is often difficult to deconvolute it into individual signals with specific points of origin. Single cell multi-omic data can provide a profile of the perturbational effects, but does not necessarily indicate the initial point of interference within the network. The objective of this project is to take advantage of large scale and genome-wide perturbational datasets by using them to train a tuned machine learning model that is capable of predicting the effects of unseen perturbations in new data. Perturb-Seq datasets are large libraries of …
Active Discovering New Slots For Task-Oriented Conversation,
2024
Singapore Management University
Active Discovering New Slots For Task-Oriented Conversation, Yuxia Wu, Tianhao Dai, Zhedong Zheng, Lizi Liao
Research Collection School Of Computing and Information Systems
Existing task-oriented conversational systems heavily rely on domain ontologies with pre-defined slots and candidate values. In practical settings, these prerequisites are hard to meet, due to the emerging new user requirements and ever-changing scenarios. To mitigate these issues for better interaction performance, there are efforts working towards detecting out-of-vocabulary values or discovering new slots under unsupervised or semi-supervised learning paradigms. However, overemphasizing on the conversation data patterns alone induces these methods to yield noisy and arbitrary slot results. To facilitate the pragmatic utility, real-world systems tend to provide a stringent amount of human labeling quota, which offers an authoritative way …
Screening Through A Broad Pool: Towards Better Diversity For Lexically Constrained Text Generation,
2024
Singapore Management University
Screening Through A Broad Pool: Towards Better Diversity For Lexically Constrained Text Generation, Changsen Yuan, Heyan Huang, Yixin Cao, Qianwen Cao
Research Collection School Of Computing and Information Systems
Lexically constrained text generation (CTG) is to generate text that contains given constrained keywords. However, the text diversity of existing models is still unsatisfactory. In this paper, we propose a lightweight dynamic refinement strategy that aims at increasing the randomness of inference to improve generation richness and diversity while maintaining a high level of fluidity and integrity. Our basic idea is to enlarge the number and length of candidate sentences in each iteration, and choose the best for subsequent refinement. On the one hand, different from previous works, which carefully insert one token between two words per action, we insert …
Conditional Neural Heuristic For Multiobjective Vehicle Routing Problems,
2024
Singapore Management University
Conditional Neural Heuristic For Multiobjective Vehicle Routing Problems, Mingfeng Fan, Yaoxin Wu, Zhiguang Cao, Wen Song, Guillaume Sartoretti, Huan Liu, Guohua Wu
Research Collection School Of Computing and Information Systems
Existing neural heuristics for multiobjective vehicle routing problems (MOVRPs) are primarily conditioned on instance context, which failed to appropriately exploit preference and problem size, thus holding back the performance. To thoroughly unleash the potential, we propose a novel conditional neural heuristic (CNH) that fully leverages the instance context, preference, and size with an encoder–decoder structured policy network. Particularly, in our CNH, we design a dual-attention-based encoder to relate preferences and instance contexts, so as to better capture their joint effect on approximating the exact Pareto front (PF). We also design a size-aware decoder based on the sinusoidal encoding to explicitly …
Win: Weight-Decay-Integrated Nesterov Acceleration For Faster Network Training,
2024
Singapore Management University
Win: Weight-Decay-Integrated Nesterov Acceleration For Faster Network Training, Pan Zhou, Xingyu Xie, Zhouchen Lin, Kim-Chuan Toh, Shuicheng Yan
Research Collection School Of Computing and Information Systems
Training deep networks on large-scale datasets is computationally challenging. This work explores the problem of “how to accelerate adaptive gradient algorithms in a general manner", and proposes an effective Weight-decay-Integrated Nesterov acceleration (Win) to accelerate adaptive algorithms. Taking AdamW and Adam as examples, per iteration, we construct a dynamical loss that combines the vanilla training loss and a dynamic regularizer inspired by proximal point method, and respectively minimize the first- and second-order Taylor approximations of dynamical loss to update variable. This yields our Win acceleration that uses a conservative step and an aggressive step to update, and linearly combines these …
Faster Rates For Compressed Federated Learning With Client-Variance Reduction,
2024
Singapore Management University
Faster Rates For Compressed Federated Learning With Client-Variance Reduction, Haoyu Zhao, Konstantin Burlachenko, Zhize Li, Peter Richtarik
Research Collection School Of Computing and Information Systems
Due to the communication bottleneck in distributed and federated learning applications, algorithms using communication compression have attracted significant attention and are widely used in practice. Moreover, the huge number, high heterogeneity, and limited availability of clients result in high client -variance. This paper addresses these two issues together by proposing compressed and clientvariance reduced methods COFIG and FRECON. We prove an O( (1+\omega)3/2\surdN+ (1+\omega)N2/3 S\epsilon2 S\epsilon2 ) bound on the number of communication rounds of COFIG in the nonconvex setting, where N is the total number of clients, S is the number of clients participating in each round, \epsilon is …
Music Genre Classification Capabilities Of Enhanced Neural Network Architectures,
2024
University of Minnesota Morris
Music Genre Classification Capabilities Of Enhanced Neural Network Architectures, Joshua Engelkes
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
With the increase of digital music audio uploads, applications that deal with music information have been widely requested by streaming platforms. Automatic music genre classification is an important function of music recommendation and music search applications. Since the music genre categorization criteria continually shift, data-driven methods such as neural networks have been proven especially useful to music information retrieval. An enhanced CNN architecture, the Bottom-up Broadcast Neural Network, uses mel-spectrograms to push music data through a network where important low-level information is preserved. An enhanced RNN architecture, the Independent Recurrent Neural Network for Music Genre Classification, takes advantage of the …
Dl-Drl: A Double-Level Deep Reinforcement Learning Approach For Large-Scale Task Scheduling Of Multi-Uav,
2024
Central South University
Dl-Drl: A Double-Level Deep Reinforcement Learning Approach For Large-Scale Task Scheduling Of Multi-Uav, Xiao Mao, Guohua Wu, Mingfeng Fan, Zhiguang Cao, Witold Pedrycz
Research Collection School Of Computing and Information Systems
Exploiting unmanned aerial vehicles (UAVs) to execute tasks is gaining growing popularity recently. To address the underlying task scheduling problem, conventional exact and heuristic algorithms encounter challenges such as rapidly increasing computation time and heavy reliance on domain knowledge, particularly when dealing with large-scale problems. The deep reinforcement learning (DRL) based methods that learn useful patterns from massive data demonstrate notable advantages. However, their decision space will become prohibitively huge as the problem scales up, thus deteriorating the computation efficiency. To alleviate this issue, we propose a double-level deep reinforcement learning (DL-DRL) approach based on a divide and conquer framework …
Recommendations With Minimum Exposure Guarantees: A Post-Processing Framework,
2024
Singapore Management University
Recommendations With Minimum Exposure Guarantees: A Post-Processing Framework, Ramon Lopes, Rodrigo Alves, Antoine Ledent, Rodrygo L. T. Santos, Marius Kloft
Research Collection School Of Computing and Information Systems
Relevance-based ranking is a popular ingredient in recommenders, but it frequently struggles to meet fairness criteria because social and cultural norms may favor some item groups over others. For instance, some items might receive lower ratings due to some sort of bias (e.g. gender bias). A fair ranking should balance the exposure of items from advantaged and disadvantaged groups. To this end, we propose a novel post-processing framework to produce fair, exposure-aware recommendations. Our approach is based on an integer linear programming model maximizing the expected utility while satisfying a minimum exposure constraint. The model has fewer variables than previous …
Imitate The Good And Avoid The Bad: An Incremental Approach To Safe Reinforcement Learning,
2024
Singapore Management University
Imitate The Good And Avoid The Bad: An Incremental Approach To Safe Reinforcement Learning, Minh Huy Hoang, Mai Anh Tien, Pradeep Varakantham
Research Collection School Of Computing and Information Systems
A popular framework for enforcing safe actions in Reinforcement Learning (RL) is Constrained RL, where trajectory based constraints on expected cost (or other cost measures) are employed to enforce safety and more importantly these constraints are enforced while maximizing expected reward. Most recent approaches for solving Constrained RL convert the trajectory based cost constraint into a surrogate problem that can be solved using minor modifications to RL methods. A key drawback with such approaches is an over or underestimation of the cost constraint at each state. Therefore, we provide an approach that does not modify the trajectory based cost constraint …
