Artificial Intelligence and Robotics Commons^™

Node-Wise Localization Of Graph Neural Networks, Zemin Liu, Yuan Fang, Chenghao Liu, Steven C.H. Hoi

Research Collection School Of Computing and Information Systems

Graph neural networks (GNNs) emerge as a powerful family of representation learning models on graphs. To derive node representations, they utilize a global model that recursively aggregates information from the neighboring nodes. However, different nodes reside at different parts of the graph in different local contexts, making their distributions vary across the graph. Ideally, how a node receives its neighborhood information should be a function of its local context, to diverge from the global GNN model shared by all nodes. To utilize node locality without overfitting, we propose a node-wise localization of GNNs by accounting for both global and local …

Automated Taxi Queue Management At High-Demand Venues, Mengyu Ji, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

In this paper, we seek to identify an effective management policy that could reduce supply-demand gaps at taxi queues serving high-density locations where demand surges frequently happen. Unlike current industry practice, which relies on broadcasting to attract taxis to come and serve the queue, we propose more proactive and adaptive approaches to handle demand surges. Our design objective is to reduce the cumulative supply-demand gaps as much as we could by sending notifications to individual taxis. To address this problem, we first propose a highly effective passenger demand prediction system that is based on the real-time flight arrival information. By …

Identification Of Chemical Structures And Substructures Via Deep Q-Learning And Supervised Learning Of Ftir Spectra, Joshua D. Ellis

Graduate Theses/Dissertations

Fourier-transform infrared (FTIR) spectra of organic compounds can be used to compare and identify compounds. A mid-FTIR spectrum gives absorbance values of a compound over the 400-4000 cm^-1 range. Spectral matching is the process of comparing the spectral signature of two or more compounds and returning a value for the similarity of the compounds based on how closely their spectra match. This process is commonly used to identify an unknown compound by searching for its spectrum’s closes match in a database of known spectra. A major limitation of this process is that it can only be used to identify …

Fast Magnetic Resonance Image Reconstruction With Deep Learning Using An Efficientnet Encoder, Tahsin Rahman

Open Access Theses & Dissertations

This thesis aims to develop an efficient, deep network based method for Magnetic Resonance Imaging (MRI) acceleration through undersampled MR image reconstruction. Deep Neural Networks, particularly Deep Convolutional Networks, have been demonstrated to be highly effective in a wide variety of computer vision tasks, including MRI reconstruction. However, modern highly efficient encoder structures, such as the EfficientNet can potentially reduce reconstruction times further while improving reconstruction quality. To that end, we have developed a multi-channel U-Net MRI reconstruction network which uses an EfficientNet encoder and a custom asymmetric. The network was trained and tested using 5x undersampled multi-channel brain MR …

Selecting Robust Strategies When Players Do Not Know Exactly What Game They Are Playing, Oscar Samuel Veliz

Open Access Theses & Dissertations

Game theory is a tool for modeling multi-agent decision problems and has been used to great success in modeling and simulating problems such as poker, security, and trading agents. However, many real games are extremely large and complex with multiple agent interactions. One approach for solving these games is to use abstraction techniques to shrink the game to a form that can be solved by removing details and translating a solution back to the original.However, abstraction introduces error into the model. This research studies ways to analyze games, abstractions, and strategies that are robust to noise in the game.

Gaining …

Explainable Deep Few-Shot Anomaly Detection With Deviation Networks, Guansong Pang, Choubo Ding, Chunhua Shen, Anton Van Den Hengel

Research Collection School Of Computing and Information Systems

Existing anomaly detection paradigms overwhelmingly focus on training detection models using exclusively normal data or unlabeled data (mostly normal samples). One notorious issue with these approaches is that they are weak in discriminating anomalies from normal samples due to the lack of the knowledge about the anomalies. Here, we study the problem of few-shot anomaly detection, in which we aim at using a few labeled anomaly examples to train sample-efficient discriminative detection models. To address this problem, we introduce a novel weakly-supervised anomaly detection framework to train detection models without assuming the examples illustrating all possible classes of anomaly.Specifically, the …

Anomaly And Novelty Detection, Explanation, And Accommodation (Andea), Guansong Pang, Jundong Li, Anton Van Den Hengel, Longbing Cao, Thomas G. Dietterich

Research Collection School Of Computing and Information Systems

The detection of, explanation of, and accommodation to anomalies and novelties are active research areas in multiple communities, including data mining, machine learning, and computer vision. They are applied in various guises including anomaly detection, out-of-distribution example detection, adversarial example recognition and detection, curiosity-driven reinforcement learning, and open-set recognition and adaptation, all of which are of great interest to the SIGKDD community. The techniques developed have been applied in a wide range of domains including fraud detection and anti-money laundering in fintech, early disease detection, intrusion detection in large-scale computer networks and data centers, defending AI systems from adversarial attacks, …

Toward Deep Supervised Anomaly Detection: Reinforcement Learning From Partially Labeled Anomaly Data, Guansong Pang, Anton Van Den Hengel, Chunhua Shen, Longbing Cao

Research Collection School Of Computing and Information Systems

We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either exclusively fit the limited anomaly examples that typically do not span the entire set of anomalies, or proceed with unsupervised learning from the unlabeled data. We propose here instead a deep reinforcement learning-based approach that enables an end-to-end optimization of the detection of both labeled and unlabeled anomalies. This approach learns the known abnormality by automatically interacting with an anomalybiased simulation environment, while continuously extending the …

Reproducibility Companion Paper: Knowledge Enhanced Neural Fashion Trend Forecasting, Yunshan Ma, Yujuan Ding, Xun Yang, Lizi Liao, Wai Keung Wong, Tat-Seng Chua, Jinyoung Moon, Hong-Han Shuai

Research Collection School Of Computing and Information Systems

This companion paper supports the replication of the fashion trend forecasting experiments with the KERN (Knowledge Enhanced Recurrent Network) method that we presented in the ICMR 2020. We provide an artifact that allows the replication of the experiments using a Python implementation. The artifact is easy to deploy with simple installation, training and evaluation. We reproduce the experiments conducted in the original paper and obtain similar performance as previously reported. The replication results of the experiments support the main claims in the original paper.

Learning Interpretable Concept Groups In Cnns, Saurabh Varshneya, Antoine Ledent, Rob Vandermeulen, Yunwen Lei, Matthias Enders, Damian Borth, Marius Kloft

Research Collection School Of Computing and Information Systems

We propose a novel training methodology---Concept Group Learning (CGL)---that encourages training of interpretable CNN filters by partitioning filters in each layer into concept groups, each of which is trained to learn a single visual concept. We achieve this through a novel regularization strategy that forces filters in the same group to be active in similar image regions for a given layer. We additionally use a regularizer to encourage a sparse weighting of the concept groups in each layer so that a few concept groups can have greater importance than others. We quantitatively evaluate CGL's model interpretability using standard interpretability evaluation …

Fine-Grained Analysis Of Structured Output Prediction, Waleed Mustafa, Yunwen Lei, Antoine Ledent, Marius And Kloft

Research Collection School Of Computing and Information Systems

In machine learning we often encounter structured output prediction problems (SOPPs), i.e. problems where the output space admits a rich internal structure. Application domains where SOPPs naturally occur include natural language processing, speech recognition, and computer vision. Typical SOPPs have an extremely large label set, which grows exponentially as a function of the size of the output. Existing generalization analysis implies generalization bounds with at least a square-root dependency on the cardinality d of the label set, which can be vacuous in practice. In this paper, we significantly improve the state of the art by developing novel high-probability bounds with …

Integrating Empirical Analysis Into Analytical Framework: An Integrated Model Structure For On-Demand Transportation, Yuliu Su, Ying Xu, Costas Courcoubetis, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

On-demand transportation services have been developing in an irresistible trend since their first launch in public. These services not only transform the urban mobility landscape, but also profoundly change individuals’ travel behavior. In this paper, we propose an integrated model structure which integrates empirical analysis into a discrete choice based analytical framework to investigate a heterogeneous population’s choices on ownership, usage and transportation mode with the presence of ride-hailing. Distinguished from traditional discrete choice models where individuals’ choices are only affected by exogenous variables and are independent of other individuals’ choices, our model extends to capture the endogeneity of supply …

A Lagrangian Column Generation Approach For The Probabilistic Crowdsourced Logistics Planning, Chung-Kyun Han, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

In recent years we have increasingly seen the movement for the retail industry to move their operations online. Along the process, it has created brand new patterns for the fulfillment service, and the logistics service providers serving these retailers have no choice but to adapt. The most challenging issues faced by all logistics service providers are the highly fluctuating demands and the shortening response times. All these challenges imply that maintaining a fixed fleet will either be too costly or insufficient. One potential solution is to tap into the crowdsourced workforce. However, existing industry practices of relying on human planners …

Learning To Assign: Towards Fair Task Assignment In Large-Scale Ride Hailing, Dingyuan Shi, Yongxin Tong, Zimu Zhou, Bingchen Song, Weifeng Lv, Qiang Yang

Research Collection School Of Computing and Information Systems

Ride hailing is a widespread shared mobility application where the central issue is to assign taxi requests to drivers with various objectives. Despite extensive research on task assignment in ride hailing, the fairness of earnings among drivers is largely neglected. Pioneer studies on fair task assignment in ride hailing are ineffective and inefficient due to their myopic optimization perspective and timeconsuming assignment techniques. In this work, we propose LAF, an effective and efficient task assignment scheme that optimizes both utility and fairness. We adopt reinforcement learning to make assignments in a holistic manner and propose a set of acceleration techniques …

Biasrv: Uncovering Biased Sentiment Predictions At Runtime, Zhou Yang, Muhammad Hilmi Asyrofi, David Lo

Research Collection School Of Computing and Information Systems

Sentiment analysis (SA) systems, though widely applied in many domains, have been demonstrated to produce biased results. Some research works have been done in automatically generating test cases to reveal unfairness in SA systems, but the community still lacks tools that can monitor and uncover biased predictions at runtime. This paper fills this gap by proposing BiasRV, the first tool to raise an alarm when a deployed SA system makes a biased prediction on a given input text. To implement this feature, BiasRV dynamically extracts a template from an input text and from the template generates gender-discriminatory mutants (semanticallyequivalent texts …

Crossasr++: A Modular Differential Testing Framework For Automatic Speech Recognition, Muhammad Hilmi Asyrofi, Zhou Yang, David Lo

Research Collection School Of Computing and Information Systems

Developers need to perform adequate testing to ensure the quality of Automatic Speech Recognition (ASR) systems. However, manually collecting required test cases is tedious and time-consuming. Our recent work proposes CrossASR, a differential testing method for ASR systems. This method first utilizes Text-to-Speech (TTS) to generate audios from texts automatically and then feed these audios into different ASR systems for cross-referencing to uncover failed test cases. It also leverages a failure estimator to find failing test cases more efficiently. Such a method is inherently self-improvable: the performance can increase by leveraging more advanced TTS and ASR systems. So, in this …

Cfr-Mix: Solving Imperfect Information Extensive-Form Games With Combinatorial Action Space, Shuxin Li, Youzhi Zhang, Xinrun Wang, Wanqi Xue, Bo An

Research Collection School Of Computing and Information Systems

In many real-world scenarios, a team of agents must coordinate with each other to compete against an opponent. The challenge of solving this type of game is that the team's joint action space grows exponentially with the number of agents, which results in the inefficiency of the existing algorithms, e.g., Counterfactual Regret Minimization (CFR). To address this problem, we propose a new framework of CFR: CFR-MIX. Firstly, we propose a new strategy representation that represents a joint action strategy using individual strategies of all agents and a consistency relationship to maintain the cooperation between agents. To compute the equilibrium with …

Solving Large-Scale Extensive-Form Network Security Games Via Neural Fictitious Self-Play, Wanqi Xue, Youzhi Zhang, Shuxin Li, Xinrun Wang, Bo An, Chai Kiat Yeo

Research Collection School Of Computing and Information Systems

Securing networked infrastructures is important in the real world. The problem of deploying security resources to protect against an attacker in networked domains can be modeled as Network Security Games (NSGs). Unfortunately, existing approaches, including the deep learning-based approaches, are inefficient to solve large-scale extensive-form NSGs. In this paper, we propose a novel learning paradigm, NSG-NFSP, to solve large-scale extensive-form NSGs based on Neural Fictitious Self-Play (NFSP). Our main contributions include: i) reforming the best response (BR) policy network in NFSP to be a mapping from action-state pair to action-value, to make the calculation of BR possible in NSGs; ii) …

Neural Regret-Matching For Distributed Constraint Optimization Problems, Yanchen Deng, Runshen Yu, Xinrun Wang, Bo An

Research Collection School Of Computing and Information Systems

Distributed constraint optimization problems (DCOPs) are a powerful model for multi-agent coordination and optimization, where information and controls are distributed among multiple agents by nature. Sampling-based algorithms are important incomplete techniques for solving medium-scale DCOPs. However, they use tables to exactly store all the information (e.g., costs, confidence bounds) to facilitate sampling, which limits their scalability. This paper tackles the limitation by incorporating deep neural networks in solving DCOPs for the first time and presents a neural-based sampling scheme built upon regret-matching. In the algorithm, each agent trains a neural network to approximate the regret related to its local problem …

Learning And Exploiting Shaped Reward Models For Large Scale Multiagent Rl, Arambam James Singh, Akshat Kumar, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Many real world systems involve interaction among large number of agents to achieve a common goal, for example, air traffic control. Several model-free RL algorithms have been proposed for such settings. A key limitation is that the empirical reward signal in model-free case is not very effective in addressing the multiagent credit assignment problem, which determines an agent's contribution to the team's success. This results in lower solution quality and high sample complexity. To address this, we contribute (a) an approach to learn a differentiable reward model for both continuous and discrete action setting by exploiting the collective nature of …