A Learned Generalized Geodesic Distance Function-Based Approach For Node Feature Augmentation On Graphs,
2024
Singapore Management University
A Learned Generalized Geodesic Distance Function-Based Approach For Node Feature Augmentation On Graphs, Amitoz Azad, Yuan Fang
Research Collection School Of Computing and Information Systems
Geodesic distances on manifolds have numerous applications in image processing, computer graphics and computer vision. In this work, we introduce an approach called 'LGGD' (Learned Generalized Geodesic Distances). This method involves generating node features by learning a generalized geodesic distance function through a training pipeline that incorporates training data, graph topology and the node content features. The strength of this method lies in the proven robustness of the generalized geodesic distances to noise and outliers. Our contributions encompass improved performance in node classification tasks, competitive results with state-of-the-art methods on real-world graph datasets, the demonstration of the learnability of parameters …
Heterogeneous Graph Transformer With Poly-Tokenization,
2024
Singapore Management University
Heterogeneous Graph Transformer With Poly-Tokenization, Zhiyuan Lu, Yuan Fang, Cheng Yang, Chuan Shi
Research Collection School Of Computing and Information Systems
Graph neural networks have shown widespread success for learning on graphs, but they still face fundamental drawbacks, such as limited expressive power, over-smoothing, and over-squashing. Meanwhile, the transformer architecture offers a potential solution to these issues. However, existing graph transformers primarily cater to homogeneous graphs and are unable to model the intricate semantics of heterogeneous graphs. Moreover, unlike small molecular graphs where the entire graph can be considered as the receptive field in graph transformers, real-world heterogeneous graphs comprise a significantly larger number of nodes and cannot be entirely treated as such. Consequently, existing graph transformers struggle to capture the …
Planning Like Human : A Dual-Process Framework For Dialogue Planning,
2024
Singapore Management University
Planning Like Human : A Dual-Process Framework For Dialogue Planning, Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Ming Liu, Zerui Chen, Bing Qin
Research Collection School Of Computing and Information Systems
In proactive dialogue, the challenge lies not just in generating responses but in steering conversations toward predetermined goals, a task where Large Language Models (LLMs) typically struggle due to their reactive nature. Traditional approaches to enhance dialogue planning in LLMs, ranging from elaborate prompt engineering to the integration of policy networks, either face efficiency issues or deliver suboptimal performance. Inspired by the dual-process theory in psychology, which identifies two distinct modes of thinking—intuitive (fast) and analytical (slow), we propose the Dual-Process Dialogue Planning (DPDP) framework. DPDP embodies this theory through two complementary planning systems: an instinctive policy model for familiar …
Analyzing Temporal Complex Events With Large Language Models? A Benchmark Towards Temporal, Long Context Understanding,
2024
Singapore Management University
Analyzing Temporal Complex Events With Large Language Models? A Benchmark Towards Temporal, Long Context Understanding, Zhihan Zhang, Yixin Cao, Chenchen Ye, Ma. Yunshan, Lizi Liao, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
The digital landscape is rapidly evolving with an ever-increasing volume of online news, emphasizing the need for swift and precise analysis of complex events.We refer to the complex events composed of many news articles over an extended period as Temporal Complex Event (TCE). This paper proposes a novel approach using Large Language Models (LLMs) to systematically extract and analyze the event chain within TCE, characterized by their key points and timestamps. We establish a benchmark, named TCELongBench, to evaluate the proficiency of LLMs in handling temporal dynamics and understanding extensive text. This benchmark encompasses three distinct tasks - reading comprehension, …
Synergizing Large Language Models And Pre-Trained Smaller Models For Conversational Intent Discovery,
2024
Singapore Management University
Synergizing Large Language Models And Pre-Trained Smaller Models For Conversational Intent Discovery, Jinggui Liang, Lizi Liao, Hao Fei, Jing Jiang
Research Collection School Of Computing and Information Systems
In Conversational Intent Discovery (CID), Small Language Models (SLMs) struggle with overfitting to familiar intents and fail to label newly discovered ones. This issue stems from their limited grasp of semantic nuances and their intrinsically discriminative framework. Therefore, we propose Synergizing Large Language Models (LLMs) with pre-trained SLMs for CID (SynCID). It harnesses the profound semantic comprehension of LLMs alongside the operational agility of SLMs. By utilizing LLMs to refine both utterances and existing intent labels, SynCID significantly enhances the semantic depth, subsequently realigning these enriched descriptors within the SLMs’ feature space to correct cluster distortion and promote robust learning …
Unifying Global-Local Representations In Salient Object Detection With Transformers,
2024
Singapore Management University
Unifying Global-Local Representations In Salient Object Detection With Transformers, Sucheng Ren, Nanxuan Zhao, Qiang Wen, Guoqiang Han, Shengfeng He
Research Collection School Of Computing and Information Systems
The fully convolutional network (FCN) has dominated salient object detection for a long period. However, the locality of CNN requires the model deep enough to have a global receptive field and such a deep model always leads to the loss of local details. In this paper, we introduce a new attention-based encoder, vision transformer, into salient object detection to ensure the globalization of the representations from shallow to deep layers. With the global view in very shallow layers, the transformer encoder preserves more local representations to recover the spatial details in final saliency maps. Besides, as each layer can capture …
Speaker Verification In Agent-Generated Conversations,
2024
Singapore Management University
Speaker Verification In Agent-Generated Conversations, Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
The recent success of large language models (LLMs) has attracted widespread interest to develop role-playing conversational agents personalized to the characteristics and styles of different speakers to enhance their abilities to perform both general and special purpose dialogue tasks. However, the ability to personalize the generated utterances to speakers, whether conducted by human or LLM, has not been well studied. To bridge this gap, our study introduces a novel evaluation challenge: speaker verification in agent-generated conversations, which aimed to verify whether two sets of utterances originate from the same speaker. To this end, we assemble a large dataset collection encompassing …
Macrohft : Memory Augmented Context-Aware Reinforcement Learning On High Frequency Trading,
2024
Singapore Management University
Macrohft : Memory Augmented Context-Aware Reinforcement Learning On High Frequency Trading, Chuqiao Zong, Chaojie Wang, Molei Qin, Lei Feng, Xinrun Wang, Xinrun Wang
Research Collection School Of Computing and Information Systems
High-frequency trading (HFT) that executes algorithmic trading in short time scales, has recently occupied the majority of cryptocurrency market. Besides traditional quantitative trading methods, reinforcement learning (RL) has become another appealing approach for HFT due to its terrific ability of handling high-dimensional financial data and solving sophisticated sequential decision-making problems, e.g., hierarchical reinforcement learning (HRL) has shown its promising performance on second-level HFT by training a router to select only one sub-agent from the agent pool to execute the current transaction. However, existing RL methods for HFT still have some defects: 1) standard RL-based trading agents suffer from the overfitting …
Self-Adaptive Psro : Towards An Automatic Population-Based Game Solver,
2024
Singapore Management University
Self-Adaptive Psro : Towards An Automatic Population-Based Game Solver, Pengdeng Li, Shuxin Li, Chang Yang, Xinrun Wang, Xiao Huang, Hau Chan, Bo An
Research Collection School Of Computing and Information Systems
Policy-Space Response Oracles (PSRO) as a general algorithmic framework has achieved state-of-the-art performance in learning equilibrium policies of two-player zero-sum games. However, the hand-crafted hyperparameter value selection in most of the existing works requires extensive domain knowledge, forming the main barrier to applying PSRO to different games. In this work, we make the first attempt to investigate the possibility of self-adaptively determining the optimal hyperparameter values in the PSRO framework. Our contributions are three-fold: (1) Using several hyperparameters, we propose a parametric PSRO that unifies the gradient descent ascent (GDA) and different PSRO variants. (2) We propose the self-adaptive PSRO …
Topic Modeling On Document Networks With Dirichlet Optimal Transport Barycenter,
2024
Singapore Management University
Topic Modeling On Document Networks With Dirichlet Optimal Transport Barycenter, Ce Zhang, Hady Wirawan Lauw
Research Collection School Of Computing and Information Systems
Text documents are often interconnected in a network structure, e.g., academic papers via citations, Web pages via hyperlinks. On the one hand, though Graph Neural Networks (GNNs) have shown promising ability to derive effective embeddings for such networked documents, they do not assume a latent topic structure and result in uninterpretable embeddings. On the other hand, topic models can infer semantically interpretable topic distributions for documents by associating each topic with a group of understandable key words. However, most topic models mainly focus on plain text within documents and fail to leverage network structure across documents. Network connectivity reveals topic …
Reinforcement Nash Equilibrium Solver,
2024
Singapore Management University
Reinforcement Nash Equilibrium Solver, Xinrun Wang, Chang Yang, Shuxin Li, Pengdeng Li, Xiao Huang, Hau Chan, Bo An
Research Collection School Of Computing and Information Systems
Nash Equilibrium (NE) is the canonical solution concept of game theory, which provides an elegant tool to understand the rationalities. Though mixed strategy NE exists in any game with finite players and actions, computing NE in two- or multi-player general-sum games is PPAD-Complete. Various alternative solutions, e.g., Correlated Equilibrium (CE), and learning methods, e.g., fictitious play (FP), are proposed to approximate NE. For convenience, we call these methods as "inexact solvers", or "solvers" for short. However, the alternative solutions differ from NE and the learning methods generally fail to converge to NE. Therefore, in this work, we propose REinforcement Nash …
Ee-Lce: An Event Extraction Framework Based On Llm-Generated Cot Explanation,
2024
Singapore Management University
Ee-Lce: An Event Extraction Framework Based On Llm-Generated Cot Explanation, Yanhua Yu, Yuanlong Wang, Yunshan Ma, Jie Li, Kangkang Lu, Zhiyong Huang, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
Generative models have been widely used in event extraction. However, the interpretability of event extraction has not been fully investigated. In this paper, we propose an Event Extraction framework based on LLM-generated CoT Explanation EE-LCE, which can generate chain-of-thought-style (CoT-style) explanations for events. To this end, we provide each sample of event datasets with an explanation of the reasoning process using a large language model (LLM) GPT-3.5, and fine-tune the Flan-T5 lightweight language model (LM) supervised by the augmented dataset, enhancing both interpretability and performance of the event extraction. Moreover, we use a prefix tree (trie) to normalize the decoding …
Predicting Personality Or Prejudice? Facial Inference In The Age Of Artificial Intelligence,
2024
Singapore Management University
Predicting Personality Or Prejudice? Facial Inference In The Age Of Artificial Intelligence, Shilpa Madan, Gayoung Park
Research Collection Lee Kong Chian School Of Business
Facial inference, a cornerstone of person perception, has traditionally been studied through human judgments about personality traits and abilities based on people's faces. Recent advances in artificial intelligence (AI) have introduced new dimensions to this field, employing machine learning algorithms to reveal people's character, capabilities, and social outcomes based just on their faces. This review examines recent research on human and AI-based facial inference across psychology, business, computer science, legal, and policy studies to highlight the need for scientific consensus on whether or not people's faces can reveal their inner traits, and urges researchers to address the critical concerns …
Sociomathematical Norms And Automated Proof Checking In Mathematical Education: Reflections And Experiences,
2024
Europa-Universität Flensburg
Sociomathematical Norms And Automated Proof Checking In Mathematical Education: Reflections And Experiences, Merlin Carl
Journal of Humanistic Mathematics
According to a widely held view, mathematical proofs are essentially (indications of) formal derivations, and thus in principle mechanically checkable (this view is defended, for example, by Azzouni [3]). This should in particular hold for the kind of simple proof exercises typically given to students of mathematics learning to write proofs. If that is so, then automated proof checking should be an attractive option for math education at the undergraduate level. An opposing view would be that mathematical proofs are social objects and that what constitutes a mathematical proof can thus not be separated from the social context in which …
Maximizing Generative Ai Benefits With Task Creativity And Human Validation,
2024
Chapman University
Maximizing Generative Ai Benefits With Task Creativity And Human Validation, Charu Sinha, Veselina P. Vracheva, Cristina Nistor
Business Faculty Articles and Research
Much of the existing literature on generative AI applications is conflicting, with findings suggesting that investing in AI will lead to better organizational outcomes but also pointing out that incorporating AI may be a wasteful even counterproductive initiative. We develop a conceptual frame-work to characterize generative AI benefits based on the types of tasks that generative AI may be used for in management. Our work suggests that task creativity plays a key role in successful generative AI outcomes, but human validation - the extent to which a human engages in a supervisory role - is required to reap the benefits. …
Low-Resource Automatic Speech Recognition Domain Adaptation – A Case-Study In Aviation Maintenance,
2024
Purdue University
Low-Resource Automatic Speech Recognition Domain Adaptation – A Case-Study In Aviation Maintenance, Nadine Amin, Tracy L. Yother, Julia Rayz
Journal of Aviation/Aerospace Education & Research
With timeliness and efficiency being critical in the aviation maintenance industry, the need has been growing for smart technological solutions that optimize and streamline the different underlying tasks (Bergkvist & Sabbagh, 2021). One such task is the technical documentation of the performed maintenance operations (Chandola et al., 2022). Instead of manual documentation, voice tools that transcribe spoken logbook entries allow technicians to document their work right away in a hands-free and time efficient manner. However, an accurate automatic speech recognition (ASR) model requires large training corpora (Siyaev & Jo, 2021a), which are lacking in the domain of aviation maintenance. In …
Leveraging Generative Artificial Intelligence Models In Patient Education On Inferior Vena Cava Filters,
2024
Thomas Jefferson University
Leveraging Generative Artificial Intelligence Models In Patient Education On Inferior Vena Cava Filters, Som Singh, Aleena Jamal, Farah Qureshi, Rohma Zaidi, Fawad Qureshi
SKMC Student Presentations and Publications
Background: Inferior Vena Cava (IVC) filters have become an advantageous treatment modality for patients with venous thromboembolism. As the use of these filters continues to grow, it is imperative for providers to appropriately educate patients in a comprehensive yet understandable manner. Likewise, generative artificial intelligence models are a growing tool in patient education, but there is little understanding of the readability of these tools on IVC filters. Methods: This study aimed to determine the Flesch Reading Ease (FRE), Flesch–Kincaid, and Gunning Fog readability of IVC Filter patient educational materials generated by these artificial intelligence models. Results: The ChatGPT cohort had …
Smart Airports: Artificial Intelligence–Enabled Internet Of Things Networks Using Blockchain Technology,
2024
Independent Scholar
Smart Airports: Artificial Intelligence–Enabled Internet Of Things Networks Using Blockchain Technology, Edwin Ongola
Journal of Aviation Technology and Engineering
This article provides a perspective on how an internet of heterogeneous self-service airport terminal systems can be used for data collection, which is stored on a private or consortium blockchain depending on the ownership or operations of an airport or both. Such a setup would help to increase efficiency, reduce costs, and improve traveler experience at airport terminals. Moreover, it would allow airports to gather data directly from passengers as opposed to waiting to receive the same data from airlines. Subsequently, this data, now on a blockchain system, becomes a data source for other applications such as machine learning. In …
Personalized Driving Using Inverse Reinforcement Learning,
2024
The University of Texas Rio Grande Valley
Personalized Driving Using Inverse Reinforcement Learning, Rodrigo J. Gonzalez Salinas
Theses and Dissertations
This thesis introduces an autonomous driving controller designed to replicate individual driving behaviors based on a provided demonstration. The controller employs Inverse Reinforcement Learning (IRL) to formulate the reward function associated with the provided demonstration. IRL is implemented through a dual-feedback loop system. The inner loop utilizes Q-learning, a model-free reinforcement learning technique, to optimize the Hamilton-Jacobi-Bellman (HJB) equation and derive an appropriate control solution. The outer loop leverages this derived control solution to generate parameters for the reward function, which are subsequently integrated into the HJB equation. The ultimate control policy is deduced from the final reward function obtained …
Transforming Libraries Through Engagement: Lessons From A Library Ai Interest Group,
2024
University of Central Florida
Transforming Libraries Through Engagement: Lessons From A Library Ai Interest Group, Lily Dubach, Rachel Vacek
Faculty Scholarship and Creative Works
Learn how one academic library is engaging with its employees to explore the latest trends, tools, and topics in AI through an interest group (IG). Through stimulating discussions, webinars, guest speakers, demos, and sharing of experiences with AI, the IG empowers its library community to explore and become more comfortable with AI. This session caters to varying levels of AI expertise. Challenges, successes, and valuable insights for deeper engagement will be shared so you can learn how to establish a similar initiative in your library.
