Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Databases and Information Systems (95)
- Software Engineering (66)
- Engineering (30)
- Computer Engineering (29)
- Artificial Intelligence and Robotics (27)
-
- Graphics and Human Computer Interfaces (20)
- Information Security (20)
- Digital Communications and Networking (11)
- Social and Behavioral Sciences (9)
- Computer and Systems Architecture (7)
- Public Affairs, Public Policy and Public Administration (6)
- Theory and Algorithms (6)
- Programming Languages and Compilers (5)
- Systems Architecture (5)
- Transportation (5)
- Business (4)
- Data Storage Systems (4)
- Numerical Analysis and Scientific Computing (3)
- Communication (2)
- Management Information Systems (2)
- Medicine and Health Sciences (2)
- Public Health (2)
- Social Media (2)
- Asian Studies (1)
- Data Science (1)
- Gerontology (1)
- Health Information Technology (1)
- Keyword
-
- Neural networks (11)
- Reinforcement learning (9)
- Graph neural networks (8)
- Task analysis (7)
- Deep learning (6)
-
- Deep neural networks (5)
- Network embedding (5)
- Security (5)
- Training (5)
- Categorization (4)
- Cloud computing (4)
- Clustering (4)
- Deep learning testing (4)
- Graph Neural Networks (4)
- Neural Networks (4)
- Supervised learning (4)
- Adaptive resonance theory (3)
- Adaptive systems (3)
- Adversarial attack (3)
- Computer architecture (3)
- Data models (3)
- Deep Learning (3)
- Deep neural network (3)
- Feature extraction (3)
- Maximum likelihood estimation (3)
- Meta-learning (3)
- Networks (3)
- Recognition: Detection (3)
- Representation learning (3)
- Retrieval (3)
Articles 1 - 30 of 251
Full-Text Articles in OS and Networks
Sigmadiff: Semantics-Aware Deep Graph Matching For Pseudocode Diffing, Lian Gao, Yu Qu, Sheng Yu, Yue Duan, Heng Yin
Sigmadiff: Semantics-Aware Deep Graph Matching For Pseudocode Diffing, Lian Gao, Yu Qu, Sheng Yu, Yue Duan, Heng Yin
Research Collection School Of Computing and Information Systems
Pseudocode diffing precisely locates similar parts and captures differences between the decompiled pseudocode of two given binaries. It is particularly useful in many security scenarios such as code plagiarism detection, lineage analysis, patch, vulnerability analysis, etc. However, existing pseudocode diffing and binary diffing tools suffer from low accuracy and poor scalability, since they either rely on manually-designed heuristics (e.g., Diaphora) or heavy computations like matrix factorization (e.g., DeepBinDiff). To address the limitations, in this paper, we propose a semantics-aware, deep neural network-based model called SIGMADIFF. SIGMADIFF first constructs IR (Intermediate Representation) level interprocedural program dependency graphs (IPDGs). Then it uses …
Affinity Uncertainty-Based Hard Negative Mining In Graph Contrastive Learning, Chaoxi Niu, Guansong Pang, Ling Chen
Affinity Uncertainty-Based Hard Negative Mining In Graph Contrastive Learning, Chaoxi Niu, Guansong Pang, Ling Chen
Research Collection School Of Computing and Information Systems
Hard negative mining has shown effective in enhancing self-supervised contrastive learning (CL) on diverse data types, including graph CL (GCL). The existing hardness-aware CL methods typically treat negative instances that are most similar to the anchor instance as hard negatives, which helps improve the CL performance, especially on image data. However, this approach often fails to identify the hard negatives but leads to many false negatives on graph data. This is mainly due to that the learned graph representations are not sufficiently discriminative due to oversmooth representations and/or non-independent and identically distributed (non-i.i.d.) issues in graph data. To tackle this …
Robust Test Selection For Deep Neural Networks, Weifeng Sun, Meng Yan, Zhongxin Liu, David Lo
Robust Test Selection For Deep Neural Networks, Weifeng Sun, Meng Yan, Zhongxin Liu, David Lo
Research Collection School Of Computing and Information Systems
Deep Neural Networks (DNNs) have been widely used in various domains, such as computer vision and software engineering. Although many DNNs have been deployed to assist various tasks in the real world, similar to traditional software, they also suffer from defects that may lead to severe outcomes. DNN testing is one of the most widely used methods to ensure the quality of DNNs. Such method needs rich test inputs with oracle information (expected output) to reveal the incorrect behaviors of a DNN model. However, manually labeling all the collected test inputs is a labor-intensive task, which delays the quality assurance …
Deep Reinforcement Learning With Explicit Context Representation, Francisco Munguia-Galeano, Ah-Hwee Tan, Ze Ji
Deep Reinforcement Learning With Explicit Context Representation, Francisco Munguia-Galeano, Ah-Hwee Tan, Ze Ji
Research Collection School Of Computing and Information Systems
Though reinforcement learning (RL) has shown an outstanding capability for solving complex computational problems, most RL algorithms lack an explicit method that would allow learning from contextual information. On the other hand, humans often use context to identify patterns and relations among elements in the environment, along with how to avoid making wrong actions. However, what may seem like an obviously wrong decision from a human perspective could take hundreds of steps for an RL agent to learn to avoid. This article proposes a framework for discrete environments called Iota explicit context representation (IECR). The framework involves representing each state …
Dexbert: Effective, Task-Agnostic And Fine-Grained Representation Learning Of Android Bytecode, Tiezhu Sun, Kevin Allix, Kisub Kim, Xin Zhou, Dongsun Kim, David Lo, Tegawendé F. Bissyande, Jacques Klein
Dexbert: Effective, Task-Agnostic And Fine-Grained Representation Learning Of Android Bytecode, Tiezhu Sun, Kevin Allix, Kisub Kim, Xin Zhou, Dongsun Kim, David Lo, Tegawendé F. Bissyande, Jacques Klein
Research Collection School Of Computing and Information Systems
The automation of an increasingly large number of software engineering tasks is becoming possible thanks to Machine Learning (ML). One foundational building block in the application of ML to software artifacts is the representation of these artifacts ( e.g. , source code or executable code) into a form that is suitable for learning. Traditionally, researchers and practitioners have relied on manually selected features, based on expert knowledge, for the task at hand. Such knowledge is sometimes imprecise and generally incomplete. To overcome this limitation, many studies have leveraged representation learning, delegating to ML itself the job of automatically devising suitable …
Hyperbolic Graph Topic Modeling Network With Continuously Updated Topic Tree, Ce Zhang, Rex Ying, Hady Wirawan Lauw
Hyperbolic Graph Topic Modeling Network With Continuously Updated Topic Tree, Ce Zhang, Rex Ying, Hady Wirawan Lauw
Research Collection School Of Computing and Information Systems
Connectivity across documents often exhibits a hierarchical network structure. Hyperbolic Graph Neural Networks (HGNNs) have shown promise in preserving network hierarchy. However, they do not model the notion of topics, thus document representations lack semantic interpretability. On the other hand, a corpus of documents usually has high variability in degrees of topic specificity. For example, some documents contain general content (e.g., sports), while others focus on specific themes (e.g., basketball and swimming). Topic models indeed model latent topics for semantic interpretability, but most assume a flat topic structure and ignore such semantic hierarchy. Given these two challenges, we propose a …
Seed Selection For Testing Deep Neural Networks, Yuhan Zhi, Xiaofei Xie, Chao Shen, Jun Sun, Xiaoyu Zhang, Xiaohong Guan
Seed Selection For Testing Deep Neural Networks, Yuhan Zhi, Xiaofei Xie, Chao Shen, Jun Sun, Xiaoyu Zhang, Xiaohong Guan
Research Collection School Of Computing and Information Systems
Deep learning (DL) has been applied in many applications. Meanwhile, the quality of DL systems is becoming a big concern. To evaluate the quality of DL systems, a number of DL testing techniques have been proposed. To generate test cases, a set of initial seed inputs are required. Existing testing techniques usually construct seed corpus by randomly selecting inputs from training or test dataset. Till now, there is no study on how initial seed inputs affect the performance of DL testing and how to construct an optimal one. To fill this gap, we conduct the first systematic study to evaluate …
Cheer: Centrality-Aware High-Order Event Reasoning Network For Document-Level Event Causality Identification, Meiqi Chen, Yixin Cao, Yan Zhang, Zhiwei Liu
Cheer: Centrality-Aware High-Order Event Reasoning Network For Document-Level Event Causality Identification, Meiqi Chen, Yixin Cao, Yan Zhang, Zhiwei Liu
Research Collection School Of Computing and Information Systems
Document-level Event Causality Identification (DECI) aims to recognize causal relations between events within a document. Recent studies focus on building a document-level graph for cross-sentence reasoning, but ignore important causal structures — there are one or two “central” events that prevail throughout the document, with most other events serving as either their cause or consequence. In this paper, we manually annotate central events for a systematical investigation and propose a novel DECI model, CHEER, which performs high-order reasoning while considering event centrality. First, we summarize a general GNN-based DECI model and provide a unified view for better understanding. Second, we …
Qebverif: Quantization Error Bound Verification Of Neural Networks, Yedi Zhang, Fu Song, Jun Sun
Qebverif: Quantization Error Bound Verification Of Neural Networks, Yedi Zhang, Fu Song, Jun Sun
Research Collection School Of Computing and Information Systems
To alleviate the practical constraints for deploying deep neural networks (DNNs) on edge devices, quantization is widely regarded as one promising technique. It reduces the resource requirements for computational power and storage space by quantizing the weights and/or activation tensors of a DNN into lower bit-width fixed-point numbers, resulting in quantized neural networks (QNNs). While it has been empirically shown to introduce minor accuracy loss, critical verified properties of a DNN might become invalid once quantized. Existing verification methods focus on either individual neural networks (DNNs or QNNs) or quantization error bound for partial quantization. In this work, we propose …
Conference Report On 2022 Ieee Symposium Series On Computational Intelligence (Ieee Ssci 2022), Ah-Hwee Tan, Dipti Srinivasan, Chunyan Miao
Conference Report On 2022 Ieee Symposium Series On Computational Intelligence (Ieee Ssci 2022), Ah-Hwee Tan, Dipti Srinivasan, Chunyan Miao
Research Collection School Of Computing and Information Systems
On behalf of the organizing committee, we are delighted to deliver this conference report for the 2022 IEEE Symposium Series on Computational Intelligence (SSCI 2022), which was held in Singapore from 4th to 7th December 2022. IEEE SSCI is an established flagship annual international series of symposia on computational intelligence (CI) sponsored by the IEEE Computational Intelligence Society (CIS) to promote and stimulate discussions on the latest theory, algorithms, applications, and emerging topics on computational intelligence. After two years of virtual conferences due to the global pandemic, IEEE SSCI returned as an in-person meeting with online elements in 2022.
Towards Omni-Generalizable Neural Methods For Vehicle Routing Problems, Jianan Zhou, Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang
Towards Omni-Generalizable Neural Methods For Vehicle Routing Problems, Jianan Zhou, Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang
Research Collection School Of Computing and Information Systems
Learning heuristics for vehicle routing problems (VRPs) has gained much attention due to the less reliance on hand-crafted rules. However, existing methods are typically trained and tested on the same task with a fixed size and distribution (of nodes), and hence suffer from limited generalization performance. This paper studies a challenging yet realistic setting, which considers generalization across both size and distribution in VRPs. We propose a generic meta-learning framework, which enables effective training of an initialized model with the capability of fast adaptation to new tasks during inference. We further develop a simple yet efficient approximation method to reduce …
Context-Aware Neural Fault Localization, Zhuo Zhang, Xiaoguang Mao, Meng Yan, Xin Xia, David Lo, David Lo
Context-Aware Neural Fault Localization, Zhuo Zhang, Xiaoguang Mao, Meng Yan, Xin Xia, David Lo, David Lo
Research Collection School Of Computing and Information Systems
Numerous fault localization techniques identify suspicious statements potentially responsible for program failures by discovering the statistical correlation between test results (i.e., failing or passing) and the executions of the different statements of a program (i.e., covered or not covered). They rarely incorporate a failure context into their suspiciousness evaluation despite the fact that a failure context showing how a failure is produced is useful for analyzing and locating faults. Since a failure context usually contains the transitive relationships among the statements of causing a failure, its relationship complexity becomes one major obstacle for the context incorporation in suspiciousness evaluation of …
The Bemi Stardust: A Structured Ensemble Of Binarized Neural Networks, Ambrogio Maria Bernardelli, Stefano Gualandi, Hoong Chuin Lau, Simone Milanesi
The Bemi Stardust: A Structured Ensemble Of Binarized Neural Networks, Ambrogio Maria Bernardelli, Stefano Gualandi, Hoong Chuin Lau, Simone Milanesi
Research Collection School Of Computing and Information Systems
Binarized Neural Networks (BNNs) are receiving increasing attention due to their lightweight architecture and ability to run on low-power devices, given the fact that they can be implemented using Boolean operations. The state-of-the-art for training classification BNNs restricted to few-shot learning is based on a Mixed Integer Programming (MIP) approach. This paper proposes the BeMi ensemble, a structured architecture of classification-designed BNNs based on training a single BNN for each possible pair of classes and applying a majority voting scheme to predict the final output. The training of a single BNN discriminating between two classes is achieved by a MIP …
Link Prediction On Latent Heterogeneous Graphs, Trung Kien Nguyen, Zemin Liu, Yuan Fang
Link Prediction On Latent Heterogeneous Graphs, Trung Kien Nguyen, Zemin Liu, Yuan Fang
Research Collection School Of Computing and Information Systems
On graph data, the multitude of node or edge types gives rise to heterogeneous information networks (HINs). To preserve the heterogeneous semantics on HINs, the rich node/edge types become a cornerstone of HIN representation learning. However, in real-world scenarios, type information is often noisy, missing or inaccessible. Assuming no type information is given, we define a so-called latent heterogeneous graph (LHG), which carries latent heterogeneous semantics as the node/edge types cannot be observed. In this paper, we study the challenging and unexplored problem of link prediction on an LHG. As existing approaches depend heavily on type-based information, they are suboptimal …
Resale Hdb Price Prediction Considering Covid-19 Through Sentiment Analysis, Srinaath Anbu Durai, Zhaoxia Wang
Resale Hdb Price Prediction Considering Covid-19 Through Sentiment Analysis, Srinaath Anbu Durai, Zhaoxia Wang
Research Collection School Of Computing and Information Systems
Twitter sentiment has been used as a predictor to predict price values or trends in both the stock market and housing market. The pioneering works in this stream of research drew upon works in behavioural economics to show that sentiment or emotions impact economic decisions. Latest works in this stream focus on the algorithm used as opposed to the data used. A literature review of works in this stream through the lens of data used shows that there is a paucity of work that considers the impact of sentiments caused due to an external factor on either the stock or …
Reinforced Adaptation Network For Partial Domain Adaptation, Keyu Wu, Min Wu, Zhenghua Chen, Ruibing Jin, Wei Cui, Zhiguang Cao, Xiaoli Li
Reinforced Adaptation Network For Partial Domain Adaptation, Keyu Wu, Min Wu, Zhenghua Chen, Ruibing Jin, Wei Cui, Zhiguang Cao, Xiaoli Li
Research Collection School Of Computing and Information Systems
Domain adaptation enables generalized learning in new environments by transferring knowledge from label-rich source domains to label-scarce target domains. As a more realistic extension, partial domain adaptation (PDA) relaxes the assumption of fully shared label space, and instead deals with the scenario where the target label space is a subset of the source label space. In this paper, we propose a Reinforced Adaptation Network (RAN) to address the challenging PDA problem. Specifically, a deep reinforcement learning model is proposed to learn source data selection policies. Meanwhile, a domain adaptation model is presented to simultaneously determine rewards and learn domain-invariant feature …
On-Device Deep Multi-Task Inference Via Multi-Task Zipping, Xiaoxi He, Xu Wang, Zimu Zhou, Jiahang Wu, Zheng Yang, Lothar Thiele
On-Device Deep Multi-Task Inference Via Multi-Task Zipping, Xiaoxi He, Xu Wang, Zimu Zhou, Jiahang Wu, Zheng Yang, Lothar Thiele
Research Collection School Of Computing and Information Systems
Future mobile devices are anticipated to perceive, understand and react to the world on their own by running multiple correlated deep neural networks locally on-device. Yet the complexity of these deep models needs to be trimmed down both within-model and cross-model to fit in mobile storage and memory. Previous studies squeeze the redundancy within a single model. In this work, we aim to reduce the redundancy across multiple models. We propose Multi-Task Zipping (MTZ), a framework to automatically merge correlated, pre-trained deep neural networks for cross-model compression. Central in MTZ is a layer-wise neuron sharing and incoming weight updating scheme …
Rntrajrec: Road Network Enhanced Trajectory Recovery With Spatial-Temporal Trans-Former, Yuqi Chen, Hanyuan Zhang, Weiwei Sun, Baihua Zheng
Rntrajrec: Road Network Enhanced Trajectory Recovery With Spatial-Temporal Trans-Former, Yuqi Chen, Hanyuan Zhang, Weiwei Sun, Baihua Zheng
Research Collection School Of Computing and Information Systems
GPS trajectories are the essential foundations for many trajectory-based applications. Most applications require a large number of high sample rate trajectories to achieve a good performance. However, many real-life trajectories are collected with low sample rate due to energy concern or other constraints. We study the task of trajectory recovery in this paper as a means to increase the sample rate of low sample trajectories. Most existing works on trajectory recovery follow a sequence-to-sequence diagram, with an encoder to encode a trajectory and a decoder to recover real GPS points in the trajectory. However, these works ignore the topology of …
Generalizing Graph Neural Network Across Graphs And Time, Zhihao Wen
Generalizing Graph Neural Network Across Graphs And Time, Zhihao Wen
Research Collection School Of Computing and Information Systems
Graph-structured data widely exist in diverse real-world scenarios, analysis of these graphs can uncover valuable insights about their respective application domains. However, most previous works focused on learning node representation from a single fixed graph, while many real-world scenarios require representations to be quickly generated for unseen nodes, new edges, or entirely new graphs. This inductive ability is essential for high-throughtput machine learning systems. However, this inductive graph representation problem is quite difficult, compared to the transductive setting, for that generalizing to unseen nodes requires new subgraphs containing the new nodes to be aligned to the neural network trained already. …
Learning And Understanding User Interface Semantics From Heterogeneous Networks With Multimodal And Positional Attributes, Meng Kiat Gary Ang, Ee-Peng Lim
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, …
Effective Graph Kernels For Evolving Functional Brain Networks, Xinlei Wang, Jinyi Chen, Bing Tian Dai, Junchang Xin, Yu Gu, Ge Yu
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 …
Learning Feature Embedding Refiner For Solving Vehicle Routing Problems, Jingwen Li, Yining Ma, Zhiguang Cao, Yaoxin Wu, Wen Song, Jie Zhang, Yeow Meng Chee
Learning Feature Embedding Refiner For Solving Vehicle Routing Problems, Jingwen Li, Yining Ma, Zhiguang Cao, Yaoxin Wu, Wen Song, Jie Zhang, Yeow Meng Chee
Research Collection School Of Computing and Information Systems
While the encoder–decoder structure is widely used in the recent neural construction methods for learning to solve vehicle routing problems (VRPs), they are less effective in searching solutions due to deterministic feature embeddings and deterministic probability distributions. In this article, we propose the feature embedding refiner (FER) with a novel and generic encoder–refiner–decoder structure to boost the existing encoder–decoder structured deep models. It is model-agnostic that the encoder and the decoder can be from any pretrained neural construction method. Regarding the introduced refiner network, we design its architecture by combining the standard gated recurrent units (GRU) cell with two new …
Segment-Wise Time-Varying Dynamic Bayesian Network With Graph Regularization, Xing Yang, Chen Zhang, Baihua Zheng
Segment-Wise Time-Varying Dynamic Bayesian Network With Graph Regularization, Xing Yang, Chen Zhang, Baihua Zheng
Research Collection School Of Computing and Information Systems
Time-varying dynamic Bayesian network (TVDBN) is essential for describing time-evolving directed conditional dependence structures in complex multivariate systems. In this article, we construct a TVDBN model, together with a score-based method for its structure learning. The model adopts a vector autoregressive (VAR) model to describe inter-slice and intra-slice relations between variables. By allowing VAR parameters to change segment-wisely over time, the time-varying dynamics of the network structure can be described. Furthermore, considering some external information can provide additional similarity information of variables. Graph Laplacian is further imposed to regularize similar nodes to have similar network structures. The regularized maximum a …
Learning Dynamic Multimodal Implicit And Explicit Networks For Multiple Financial Tasks, Meng Kiat Gary Ang, Ee-Peng Lim
Learning Dynamic Multimodal Implicit And Explicit Networks For Multiple Financial Tasks, Meng Kiat Gary Ang, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
Many financial f orecasting d eep l earning w orks focus on the single task of predicting stock returns for trading with unimodal numerical inputs. Investment and risk management however involves multiple financial t asks - f orecasts o f expected returns, risks and correlations of multiple stocks in portfolios, as well as important events affecting different stocks - to support decision making. Moreover, stock returns are influenced by large volumes of non-stationary time-series information from a variety of modalities and the propagation of such information across inter-company relationship networks. Such networks could be explicit - observed co-occurrences in online …
On The Robustness Of Diffusion In A Network Under Node Attacks, Alvis Logins, Yuchen Li, Panagiotis Karras
On The Robustness Of Diffusion In A Network Under Node Attacks, Alvis Logins, Yuchen Li, Panagiotis Karras
Research Collection School Of Computing and Information Systems
How can we assess a network's ability to maintain its functionality under attacks Network robustness has been studied extensively in the case of deterministic networks. However, applications such as online information diffusion and the behavior of networked public raise a question of robustness in probabilistic networks. We propose three novel robustness measures for networks hosting a diffusion under the Independent Cascade or Linear Threshold model, susceptible to attacks by an adversarial attacker who disables nodes. The outcome of such a process depends on the selection of its initiators, or seeds, by the seeder, as well as on two factors outside …
Which Neural Network Makes More Explainable Decisions? An Approach Towards Measuring Explainability, Mengdi Zhang, Jun Sun, Jingyi Wang
Which Neural Network Makes More Explainable Decisions? An Approach Towards Measuring Explainability, Mengdi Zhang, Jun Sun, Jingyi Wang
Research Collection School Of Computing and Information Systems
Neural networks are getting increasingly popular thanks to their exceptional performance in solving many real-world problems. At the same time, they are shown to be vulnerable to attacks, difficult to debug and subject to fairness issues. To improve people’s trust in the technology, it is often necessary to provide some human-understandable explanation of neural networks’ decisions, e.g., why is that my loan application is rejected whereas hers is approved? That is, the stakeholder would be interested to minimize the chances of not being able to explain the decision consistently and would like to know how often and how easy it …
Qvip: An Ilp-Based Formal Verification Approach For Quantized Neural Networks, Yedi Zhang, Zhe Zhao, Guangke Chen, Fu Song, Min Zhang, Taolue Chen, Jun Sun
Qvip: An Ilp-Based Formal Verification Approach For Quantized Neural Networks, Yedi Zhang, Zhe Zhao, Guangke Chen, Fu Song, Min Zhang, Taolue Chen, Jun Sun
Research Collection School Of Computing and Information Systems
Deep learning has become a promising programming paradigm in software development, owing to its surprising performance in solving many challenging tasks. Deep neural networks (DNNs) are increasingly being deployed in practice, but are limited on resource-constrained devices owing to their demand for computational power. Quantization has emerged as a promising technique to reduce the size of DNNs with comparable accuracy as their floating-point numbered counterparts. The resulting quantized neural networks (QNNs) can be implemented energy-efficiently. Similar to their floating-point numbered counterparts, quality assurance techniques for QNNs, such as testing and formal verification, are essential but are currently less explored. In …
Stitching Weight-Shared Deep Neural Networks For Efficient Multitask Inference On Gpu, Zeyu Wang, Xiaoxi He, Zimu Zhou, Xu Wang, Qiang Ma, Xin Miao, Zhuo Liu, Lothar Thiele, Zheng. Yang
Stitching Weight-Shared Deep Neural Networks For Efficient Multitask Inference On Gpu, Zeyu Wang, Xiaoxi He, Zimu Zhou, Xu Wang, Qiang Ma, Xin Miao, Zhuo Liu, Lothar Thiele, Zheng. Yang
Research Collection School Of Computing and Information Systems
Intelligent personal and home applications demand multiple deep neural networks (DNNs) running on resourceconstrained platforms for compound inference tasks, known as multitask inference. To fit multiple DNNs into low-resource devices, emerging techniques resort to weight sharing among DNNs to reduce their storage. However, such reduction in storage fails to translate into efficient execution on common accelerators such as GPUs. Most DNN graph rewriters are blind for multiDNN optimization, while GPU vendors provide inefficient APIs for parallel multi-DNN execution at runtime. A few prior graph rewriters suggest cross-model graph fusion for low-latency multiDNN execution. Yet they request duplication of the shared …
Joint Hyperbolic And Euclidean Geometry Contrastive Graph Neural Networks, Xiaoyu Xu, Guansong Pang, Di Wu, Mingsheng Shang
Joint Hyperbolic And Euclidean Geometry Contrastive Graph Neural Networks, Xiaoyu Xu, Guansong Pang, Di Wu, Mingsheng Shang
Research Collection School Of Computing and Information Systems
Graph Neural Networks (GNNs) have demonstrated state-of-the-art performance in a wide variety of analytical tasks. Current GNN approaches focus on learning representations in a Euclidean space, which are effective in capturing non-tree-like structural relations, but they fail to model complex relations in many real-world graphs, such as tree-like hierarchical graph structure. This paper instead proposes to learn representations in both Euclidean and hyperbolic spaces to model these two types of graph geometries. To this end, we introduce a novel approach - Joint hyperbolic and Euclidean geometry contrastive graph neural networks (JointGMC). JointGMC is enforced to learn multiple layer-wise optimal combinations …
Learning Improvement Heuristics For Solving Routing Problems, Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang, Andrew Lim
Learning Improvement Heuristics For Solving Routing Problems, Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang, Andrew Lim
Research Collection School Of Computing and Information Systems
Recent studies in using deep learning to solve routing problems focus on construction heuristics, the solutions of which are still far from optimality. Improvement heuristics have great potential to narrow this gap by iteratively refining a solution. However, classic improvement heuristics are all guided by hand-crafted rules which may limit their performance. In this paper, we propose a deep reinforcement learning framework to learn the improvement heuristics for routing problems. We design a self-attention based deep architecture as the policy network to guide the selection of next solution. We apply our method to two important routing problems, i.e. travelling salesman …