Artificial Intelligence and Robotics Commons^™

A Review On Learning To Solve Combinatorial Optimisation Problems In Manufacturing, Cong Zhang, Yaoxin Wu, Yining Ma, Wen Song, Zhang Le, Zhiguang Cao, Jie Zhang

Research Collection School Of Computing and Information Systems

An efficient manufacturing system is key to maintaining a healthy economy today. With the rapid development of science and technology and the progress of human society, the modern manufacturing system is becoming increasingly complex, posing new challenges to both academia and industry. Ever since the beginning of industrialisation, leaps in manufacturing technology have always accompanied technological breakthroughs from other fields, for example, mechanics, physics, and computational science. Recently, machine learning (ML) technology, one of the crucial subjects of artificial intelligence, has made remarkable progress in many areas. This study thoroughly reviews how ML, specifically deep (reinforcement) learning, motivates new ideas …

Learning And Understanding User Interface Semantics From Heterogeneous Networks With Multimodal And Positional Attributes, Meng Kiat Gary Ang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

User interfaces (UI) of desktop, web, and mobile applications involve a hierarchy of objects (e.g., applications, screens, view class, and other types of design objects) with multimodal (e.g., textual and visual) and positional (e.g., spatial location, sequence order, and hierarchy level) attributes. We can therefore represent a set of application UIs as a heterogeneous network with multimodal and positional attributes. Such a network not only represents how users understand the visual layout of UIs but also influences how users would interact with applications through these UIs. To model the UI semantics well for different UI annotation, search, and evaluation tasks, …

The Vehicle Routing Problem With Simultaneous Pickup And Delivery And Occasional Drivers, Vincent F. Yu, Grace Aloina, Panca Jodiawan, Aldy Gunawan, Tsung-C. Huang

Research Collection School Of Computing and Information Systems

This research addresses the Vehicle Routing Problem with Simultaneous Pickup and Delivery and Occasional Drivers (VRPSPDOD), which is inspired from the importance of addressing product returns and the emerging notion of involving available crowds to perform pickup and delivery activities in exchange for some compensation. At the depot, a set of regular vehicles is available to deliver and/or pick up customers’ goods. A set of occasional drivers, each defined by their origin, destination, and flexibility, is also able to help serve the customers. The objective of VRPSPDOD is to minimize the total traveling cost of operating regular vehicles and total …

Proactive Conversational Agents, Lizi Liao, Grace Hui Yang, Chirag Shah

Research Collection School Of Computing and Information Systems

Conversational agents, or commonly known as dialogue systems, have gained escalating popularity in recent years. Their widespread applications support conversational interactions with users and accomplishing various tasks as personal assistants. However, one key weakness in existing conversational agents is that they only learn to passively answer user queries via training on pre-collected and manually-labeled data. Such passiveness makes the interaction modeling and system-building process relatively easier, but it largely hinders the possibility of being human-like hence lowering the user engagement level. In this tutorial, we introduce and discuss methods to equip conversational agents with the ability to interact with end …

Prudex-Compass: Towards Systematic Evaluation Of Reinforcement Learning In Financial Markets, Shuo Sun, Molei Qin, Xinrun Wang, Bo An

Research Collection School Of Computing and Information Systems

The financial markets, which involve more than $90 trillion market capitals, attract the attention of innumerable investors around the world. Recently, reinforcement learning in financial markets (FinRL) has emerged as a promising direction to train agents for making profitable investment decisions. However, the evaluation of most FinRL methods only focuses on profit-related measures and ignores many critical axes, which are far from satisfactory for financial practitioners to deploy these methods into real-world financial markets. Therefore, we introduce PRUDEX-Compass, which has 6 axes, i.e., Profitability, Risk-control, Universality, Diversity, rEliability, and eXplainability, with a total of 17 measures for a systematic evaluation. …

Of Inventorship And Patent Ownership: Examining The Intersection Between Artificial Intelligence And Patent Law, Cheng Lim Saw, Zheng Wen Samuel Chan

Research Collection Yong Pung How School Of Law

Artificial intelligence (“AI”) has garnered much attention in recent years, with capabilities spanning the operation of self-driving cars to the emulation of the great artistic masters of old. The field has now been ostensibly enlarged in light of the professed abilities of AI machines to autonomously generate patentable inventions. This article examines the present state of AI technology and the suitability of existing patent law frameworks in accommodating it. Looking ahead, the authors also offer two recommendations in a bid to anticipate and resolve the challenges that future developments in AI technology might pose to patent law. In particular, the …

Topic Recommendation For Github Repositories: How Far Can Extreme Multi-Label Learning Go?, Ratnadira Widyasari, Zhipeng Zhao, Thanh Le Cong, Hong Jin Kang, David Lo

Research Collection School Of Computing and Information Systems

GitHub is one of the most popular platforms forversion control and collaboration. In GitHub, developers are ableto assign related topics to their repositories, which is helpfulfor finding similar repositories. The topics that are assigned torepositories are varied and provide salient descriptions of therepository; some topics describe the technology employed in aproject, while others describe functionality of the project, itsgoals, and its features. Topics are part of the metadata of arepository and are useful for the organization and discoverabilityof the repository. However, the number of topics is large andthis makes it challenging to assign a relevant set of topics to arepository. …

Layout Generation As Intermediate Action Sequence Prediction, Huiting Yang, Danqing Huang, Chin-Yew Lin, Shengfeng He

Research Collection School Of Computing and Information Systems

Layout generation plays a crucial role in graphic design intelligence. One important characteristic of the graphic layouts is that they usually follow certain design principles. For example, the principle of repetition emphasizes the reuse of similar visual elements throughout the design. To generate a layout, previous works mainly attempt at predicting the absolute value of bounding box for each element, where such target representation has hidden the information of higher-order design operations like repetition (e.g. copy the size of the previously generated element). In this paper, we introduce a novel action schema to encode these operations for better modeling the …

Generalizing Math Word Problem Solvers Via Solution Diversification, Zhenwen Liang, Jipeng Zhang, Lei Wang, Yan Wang, Jie Shao, Xiangliang Zhang

Research Collection School Of Computing and Information Systems

Current math word problem (MWP) solvers are usually Seq2Seq models trained by the (one-problem; one-solution) pairs, each of which is made of a problem description and a solution showing reasoning flow to get the correct answer. However, one MWP problem naturally has multiple solution equations. The training of an MWP solver with (one-problem; one-solution) pairs excludes other correct solutions, and thus limits the generalizability of the MWP solver. One feasible solution to this limitation is to augment multiple solutions to a given problem. However, it is difficult to collect diverse and accurate augment solutions through human efforts. In this paper, …

Planning And Learning For Non-Markovian Negative Side Effects Using Finite State Controllers, Aishwarya Srivastava, Sandhya Saisubramanian, Praveen Paruchuri, Akshat Kumar, Shlomo Zilberstein

Research Collection School Of Computing and Information Systems

Autonomous systems are often deployed in the open world where it is hard to obtain complete specifications of objectives and constraints. Operating based on an incomplete model can produce negative side effects (NSEs), which affect the safety and reliability of the system. We focus on mitigating NSEs in environments modeled as Markov decision processes (MDPs). First, we learn a model of NSEs using observed data that contains state-action trajectories and severity of associated NSEs. Unlike previous works that associate NSEs with state-action pairs, our framework associates NSEs with entire trajectories, which is more general and captures non-Markovian dependence on states …

Scalable And Globally Optimal Generalized L1 K-Center Clustering Via Constraint Generation In Mixed Integer Linear Programming, Aravinth Chembu, Scott Sanner, Hassan Khurran, Akshat Kumar

Research Collection School Of Computing and Information Systems

The k-center clustering algorithm, introduced over 35 years ago, is known to be robust to class imbalance prevalent in many clustering problems and has various applications such as data summarization, document clustering, and facility location determination. Unfortunately, existing k-center algorithms provide highly suboptimal solutions that can limit their practical application, reproducibility, and clustering quality. In this paper, we provide a novel scalable and globally optimal solution to a popular variant of the k-center problem known as generalized L_1 k-center clustering that uses L_1 distance and allows the selection of arbitrary vectors as cluster centers. We show that this clustering objective …

Pose- And Attribute-Consistent Person Image Synthesis, Cheng Xu, Zejun Chen, Jiajie Mai, Xuemiao Xu, Shengfeng He

Research Collection School Of Computing and Information Systems

PersonImageSynthesisaimsattransferringtheappearanceofthesourcepersonimageintoatargetpose. Existingmethods cannot handle largeposevariations and therefore suffer fromtwocritical problems: (1)synthesisdistortionduetotheentanglementofposeandappearanceinformationamongdifferentbody componentsand(2)failureinpreservingoriginalsemantics(e.g.,thesameoutfit).Inthisarticle,weexplicitly addressthesetwoproblemsbyproposingaPose-andAttribute-consistentPersonImageSynthesisNetwork (PAC-GAN).Toreduceposeandappearancematchingambiguity,weproposeacomponent-wisetransferring modelconsistingoftwostages.Theformerstagefocusesonlyonsynthesizingtargetposes,whilethelatter renderstargetappearancesbyexplicitlytransferringtheappearanceinformationfromthesourceimageto thetargetimageinacomponent-wisemanner. Inthisway,source-targetmatchingambiguityiseliminated duetothecomponent-wisedisentanglementofposeandappearancesynthesis.Second,tomaintainattribute consistency,werepresenttheinputimageasanattributevectorandimposeahigh-levelsemanticconstraint usingthisvectortoregularizethetargetsynthesis.ExtensiveexperimentalresultsontheDeepFashiondataset demonstratethesuperiorityofourmethodoverthestateoftheart,especiallyformaintainingposeandattributeconsistenciesunderlargeposevariations.

Online Hyperparameter Optimization For Class-Incremental Learning, Yaoyao Liu, Yingying Li, Bernt Schiele, Qianru Sun

Research Collection School Of Computing and Information Systems

Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase. An inherent challenge of CIL is the stability-plasticity tradeoff, i.e., CIL models should keep stable to retain old knowledge and keep plastic to absorb new knowledge. However, none of the existing CIL models can achieve the optimal tradeoff in different data-receiving settings—where typically the training-from-half (TFH) setting needs more stability, but the training-from-scratch (TFS) needs more plasticity. To this end, we design an online learning method that can adaptively optimize the tradeoff without knowing the setting as a priori. Specifically, we first introduce the …

Real-Time Hierarchical Map Segmentation For Coordinating Multi-Robot Exploration, Tianze Luo, Zichen Chen, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Coordinating a team of autonomous agents to explore an environment can be done by partitioning the map of the environment into segments and allocating the segments as targets for the individual agents to visit. However, given an unknown environment, map segmentation must be conducted in a continuous and incremental manner. In this paper, we propose a novel real-time hierarchical map segmentation method for supporting multi-agent exploration of indoor environments, wherein clusters of regions of segments are formed hierarchically from randomly sampled points in the environment. Each cluster is then assigned with a cost-utility value based on the minimum cost possible …

Safe Delivery Of Critical Services In Areas With Volatile Security Situation Via A Stackelberg Game Approach, Tien Mai, Arunesh Sinha

Research Collection School Of Computing and Information Systems

Vaccine delivery in under-resourced locations with security risks is not just challenging but also life threatening. The COVID pandemic and the need to vaccinate added even more urgency to this issue. Motivated by this problem, we propose a general framework to set-up limited temporary (vaccination) centers that balance physical security and desired (vaccine) service coverage with limited resources. We set-up the problem as a Stackelberg game between the centers operator (defender) and an adversary, where the set of centers is not fixed a priori but is part of the decision output. This results in a mixed combinatorial and continuous optimization …

A Fair Incentive Scheme For Community Health Workers, Avinandan Bose, Tracey Li, Arunesh Sinha, Tien Mai

Research Collection School Of Computing and Information Systems

Community health workers (CHWs) play a crucial role in the last mile delivery of essential health services to under-served populations in low-income countries. Many non-governmental organizations (NGOs) provide training and support to enable CHWs to deliver health services to their communities, with no charge to the recipients of the services. This includes monetary compensation for the work that CHWs perform, which is broken down into a series of well-defined tasks. In this work, we partner with a NGO D-Tree International to design a fair monetary compensation scheme for tasks performed by CHWs in the semi-autonomous region of Zanzibar in Tanzania, …

Effective Graph Kernels For Evolving Functional Brain Networks, Xinlei Wang, Jinyi Chen, Bing Tian Dai, Junchang Xin, Yu Gu, Ge Yu

Research Collection School Of Computing and Information Systems

The graph kernel of the functional brain network is an effective method in the field of neuropsychiatric disease diagnosis like Alzheimer's Disease (AD). The traditional static brain networks cannot reflect dynamic changes of brain activities, but evolving brain networks, which are a series of brain networks over time, are able to seize such dynamic changes. As far as we know, the graph kernel method is effective for calculating the differences among networks. Therefore, it has a great potential to understand the dynamic changes of evolving brain networks, which are a series of chronological differences. However, if the conventional graph kernel …

Generalization Bounds For Inductive Matrix Completion In Low-Noise Settings, Antoine Ledent, Rodrigo Alves, Yunwen Lei, Yann Guermeur, Marius Kloft

Research Collection School Of Computing and Information Systems

We study inductive matrix completion (matrix completion with side information) under an i.i.d. subgaussian noise assumption at a low noise regime, with uniform sampling of the entries. We obtain for the first time generalization bounds with the following three properties: (1) they scale like the standard deviation of the noise and in particular approach zero in the exact recovery case; (2) even in the presence of noise, they converge to zero when the sample size approaches infinity; and (3) for a fixed dimension of the side information, they only have a logarithmic dependence on the size of the matrix. Differently …

Cross-Domain Graph Anomaly Detection Via Anomaly-Aware Contrastive Alignment, Qizhou Wang, Guansong Pang, Mahsa Salehi, Wray Buntine, Christopher Leckie

Research Collection School Of Computing and Information Systems

Cross-domain graph anomaly detection (CD-GAD) describes the problem of detecting anomalous nodes in an unlabelled target graph using auxiliary, related source graphs with labelled anomalous and normal nodes. Although it presents a promising approach to address the notoriously high false positive issue in anomaly detection, little work has been done in this line of research. There are numerous domain adaptation methods in the literature, but it is difficult to adapt them for GAD due to the unknown distributions of the anomalies and the complex node relations embedded in graph data. To this end, we introduce a novel domain adaptation approach, …

Solving Large-Scale Pursuit-Evasion Games Using Pre-Trained Strategies, Shuxin Li, Xinrun Wang, Youzhi Zhang, Wanqi Xue, Jakub Cerny, Bo An

Research Collection School Of Computing and Information Systems

Pursuit-evasion games on graphs model the coordination of police forces chasing a fleeing felon in real-world urban settings, using the standard framework of imperfect-information extensive-form games (EFGs). In recent years, solving EFGs has been largely dominated by the Policy-Space Response Oracle (PSRO) methods due to their modularity, scalability, and favorable convergence properties. However, even these methods quickly reach their limits when facing large combinatorial strategy spaces of the pursuit-evasion games. To improve their efficiency, we integrate the pre-training and fine-tuning paradigm into the core module of PSRO -- the repeated computation of the best response. First, we pre-train the pursuer's …

Alignment-Enriched Tuning For Patch-Level Pre-Trained Document Image Models, Lei Wang, Jiabang He, Xing Xu, Ning Liu, Hui Liu

Research Collection School Of Computing and Information Systems

Alignment between image and text has shown promising im provements on patch-level pre-trained document image mod els. However, investigating more effective or finer-grained alignment techniques during pre-training requires a large amount of computation cost and time. Thus, a question natu rally arises: Could we fine-tune the pre-trained models adap tive to downstream tasks with alignment objectives and achieve comparable or better performance? In this paper, we pro pose a new model architecture with alignment-enriched tuning (dubbed AETNet) upon pre-trained document image models, to adapt downstream tasks with the joint task-specific super vised and alignment-aware contrastive objective. Specifically, weintroduce an extra …

Legal Dispositionism And Artificially-Intelligent Attributions, Jerrold Soh

Research Collection Yong Pung How School Of Law

It is conventionally argued that because an artificially-intelligent (AI) system acts autonomously, its makers cannot easily be held liable should the system's actions harm. Since the system cannot be liable on its own account either, existing laws expose victims to accountability gaps and need to be reformed. Recent legal instruments have nonetheless established obligations against AI developers and providers. Drawing on attribution theory, this paper examines how these seemingly opposing positions are shaped by the ways in which AI systems are conceptualised. Specifically, folk dispositionism underpins conventional legal discourse on AI liability, personality, publications, and inventions and leads us towards …

Constrained Reinforcement Learning In Hard Exploration Problems, Pankayaraj Pathmanathan, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

One approach to guaranteeing safety in Reinforcement Learning is through cost constraints that are imposed on trajectories. Recent works in constrained RL have developed methods that ensure constraints can be enforced even at learning time while maximizing the overall value of the policy. Unfortunately, as demonstrated in our experimental results, such approaches do not perform well on complex multi-level tasks, with longer episode lengths or sparse rewards. To that end, wepropose a scalable hierarchical approach for constrained RL problems that employs backward cost value functions in the context of task hierarchy and a novel intrinsic reward function in lower levels …

Research@Smu: Sustainable Living, Singapore Management University

Research Collection Office of Research

Sustainable Living is one of the three key priorities of the SMU 2025 Strategy, and the University is committed to develop it into an area of cross-disciplinary strength. The articles in this booklet highlight impactful sustainability research accomplishments at SMU, which spans five broad pillars: Sustainable Business Operations; Sustainable Finance and Impact Assessment; Sustainable Ageing and Wellness; Sustainable Urban Infrastructure; and Sustainable Agro-business and Food Consumption.

Contents:

Sustainable Business Operations

• Managing the Load on Loading Bays
• Going the Last-mile
• Feeding a Growing World
• Pooling the Benefits of Sharing a Ride

Sustainable Finance and Impact Assessment

• When Going Green Becomes a …

Seven Pillars For The Future Of Artificial Intelligence, Erik Cambria, Rui Mao, Melvin Chen, Zhaoxia Wang, Seng-Beng Ho

Research Collection School Of Computing and Information Systems

In recent years, AI research has showcased tremendous potential to impact positively humanity and society. Although AI frequently outperforms humans in tasks related to classification and pattern recognition, it continues to face challenges when dealing with complex tasks such as intuitive decision-making, sense disambiguation, sarcasm detection, and narrative understanding, as these require advanced kinds of reasoning, e.g., commonsense reasoning and causal reasoning, which have not been emulated satisfactorily yet. To address these shortcomings, we propose seven pillars that we believe represent the key hallmark features for the future of AI, namely: Multidisciplinarity, Task Decomposition, Parallel Analogy, Symbol Grounding, Similarity Measure, …

The Three-Sided Market Of On-Demand Delivery, S. Bahrami, M. Nourinejad, Y. Yin, Hai Wang

Research Collection School Of Computing and Information Systems

On-demand delivery services are three-sided markets that enable interactions between customers and suppliers with the help of crowdsourced drivers. Customers and suppliers may pay a commission to gain access to the service and drivers are granted a wage for providing their delivery service. This study characterizes the properties of three-side on-demand delivery markets, and proposes pricing strategies that enable the platform to manipulate the market towards profit or social welfare maximizing outcomes. We consider earning-sensitive independent drivers, price-and-time-sensitive customers, and price-sensitive suppliers. By assuming that all players are heterogeneous in their valuation of the service, we model their numbers as …

I Know What You Are Searching For: Code Snippet Recommendation From Stack Overflow Posts, Zhipeng Gao, Xin Xia, David Lo, John C. Grundy, Xindong Zhang, Zhenchang Xing

Research Collection School Of Computing and Information Systems

Stack Overflow has been heavily used by software developers to seek programming-related information. More and more developers use Community Question and Answer forums, such as Stack Overflow, to search for code examples of how to accomplish a certain coding task. This is often considered to be more efficient than working from source documentation, tutorials, or full worked examples. However, due to the complexity of these online Question and Answer forums and the very large volume of information they contain, developers can be overwhelmed by the sheer volume of available information. This makes it hard to find and/or even be aware …

Neighborhood Retail Amenities And Taxi Trip Behavior: A Natural Experiment In Singapore, Kwan Ok Lee, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

While a small change in land use planning in existing neighborhoods may significantly reduce private vehicle trips, we do not have a great understanding of the magnitude of the project- and shock-based causal change in travel behaviors, especially for the retail purpose. We analyze the impact of newly developed malls on the retail trip behavior of nearby residents for shopping, dining or services. Using the difference-in-differences approach and big data from a major taxi company in Singapore, we find that households residing within 800 m from a new mall are significantly less likely to take taxis to other retail destinations …

Aspect Sentiment Triplet Extraction Incorporating Syntactic Constituency Parsing Tree And Commonsense Knowledge Graph, Zhenda Hu, Zhaoxia Wang, Yinglin Wang, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

The aspect sentiment triplet extraction (ASTE) task aims to extract the target term and the opinion term, and simultaneously identify the sentiment polarity of target-opinion pairs from the given sentences. While syntactic constituency information and commonsense knowledge are both important and valuable for the ASTE task, only a few studies have explored how to integrate them via flexible graph convolutional networks (GCNs) for this task. To address this gap, this paper proposes a novel end-to-end model, namely GCN-EGTS, which is an enhanced Grid Tagging Scheme (GTS) for ASTE leveraging syntactic constituency parsing tree and a commonsense knowledge graph based on …

Reinforcement Learning Enhanced Pichunter For Interactive Search, Zhixin Ma, Jiaxin Wu, Weixiong Loo, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

With the tremendous increase in video data size, search performance could be impacted significantly. Specifically, in an interactive system, a real-time system allows a user to browse, search and refine a query. Without a speedy system quickly, the main ingredient to engage a user to stay focused, an interactive system becomes less effective even with a sophisticated deep learning system. This paper addresses this challenge by leveraging approximate search, Bayesian inference, and reinforcement learning. For approximate search, we apply a hierarchical navigable small world, which is an efficient approximate nearest neighbor search algorithm. To quickly prune the search scope, we …