Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (8526)
- Computer Sciences (8509)
- Databases and Information Systems (3448)
- Software Engineering (2153)
- Artificial Intelligence and Robotics (1686)
-
- Information Security (1060)
- Numerical Analysis and Scientific Computing (1024)
- Graphics and Human Computer Interfaces (926)
- Engineering (887)
- Social and Behavioral Sciences (681)
- Business (641)
- Theory and Algorithms (493)
- Computer Engineering (450)
- Operations Research, Systems Engineering and Industrial Engineering (410)
- Programming Languages and Compilers (379)
- OS and Networks (323)
- Communication (297)
- Social Media (240)
- Public Affairs, Public Policy and Public Administration (217)
- Transportation (195)
- Medicine and Health Sciences (178)
- Education (168)
- Management Information Systems (166)
- Data Storage Systems (161)
- E-Commerce (148)
- International and Area Studies (111)
- Asian Studies (110)
- Health Information Technology (107)
- Digital Communications and Networking (104)
- Technology and Innovation (104)
- Keyword
-
- Deep learning (123)
- Machine learning (121)
- Social media (74)
- Artificial intelligence (71)
- Reinforcement learning (69)
-
- Data mining (64)
- Privacy (61)
- Cloud computing (58)
- Deep Learning (56)
- Empirical study (54)
- Optimization (54)
- Security (53)
- Visualization (51)
- Online learning (49)
- Software engineering (49)
- Training (49)
- Neural networks (48)
- Singapore (48)
- Task analysis (48)
- Anomaly detection (47)
- Twitter (46)
- Feature extraction (45)
- Large Language Models (45)
- Blockchain (44)
- Collaboration (44)
- Semantics (43)
- Access control (41)
- Algorithms (40)
- Android (39)
- Classification (38)
- Publication Year
- File Type
Articles 1321 - 1350 of 8567
Full-Text Articles in Entire DC Network
Streamlining Java Programming: Uncovering Well-Formed Idioms With Idiomine, Yanming Yang, Xing Hu, Xin Xia, David Lo, Xiaohu Yang
Streamlining Java Programming: Uncovering Well-Formed Idioms With Idiomine, Yanming Yang, Xing Hu, Xin Xia, David Lo, Xiaohu Yang
Research Collection School Of Computing and Information Systems
Code idioms are commonly used patterns, techniques, or practices that aid in solving particular problems or specific tasks across multiple software projects. They can improve code quality, performance, and maintainability, and also promote program standardization and reuse across projects. However, identifying code idioms is significantly challenging, as existing studies have still suffered from three main limitations. First, it is difficult to recognize idioms that span non-contiguous code lines. Second, identifying idioms with intricate data flow and code structures can be challenging. Moreover, they only extract dataset-specific idioms, so common idioms or well-established code/design patterns that are rarely found in datasets …
Curiosity-Driven Testing For Sequential Decision-Making Process, Junda He, Zhou Yang, Jieke Shi, Chengran Yang, Kisub Kim, Bowen Xu, Xin Zhou, David Lo
Curiosity-Driven Testing For Sequential Decision-Making Process, Junda He, Zhou Yang, Jieke Shi, Chengran Yang, Kisub Kim, Bowen Xu, Xin Zhou, David Lo
Research Collection School Of Computing and Information Systems
Sequential decision-making processes (SDPs) are fundamental for complex real-world challenges, such as autonomous driving, robotic control, and traffic management. While recent advances in Deep Learning (DL) have led to mature solutions for solving these complex problems, SDMs remain vulnerable to learning unsafe behaviors, posing significant risks in safety-critical applications. However, developing a testing framework for SDMs that can identify a diverse set of crash-triggering scenarios remains an open challenge. To address this, we propose CureFuzz, a novel curiosity-driven black-box fuzz testing approach for SDMs. CureFuzz proposes a curiosity mechanism that allows a fuzzer to effectively explore novel and diverse scenarios, …
Deep Reinforcement Learning For Dynamic Algorithm Selection: A Proof-Of-Principle Study On Differential Evolution, Hongshu Guo, Yining Ma, Zeyuan Ma, Jiacheng Chen, Xinglin Zhang, Zhiguang Cao, Jun Zhang, Yue-Jiao Gong
Deep Reinforcement Learning For Dynamic Algorithm Selection: A Proof-Of-Principle Study On Differential Evolution, Hongshu Guo, Yining Ma, Zeyuan Ma, Jiacheng Chen, Xinglin Zhang, Zhiguang Cao, Jun Zhang, Yue-Jiao Gong
Research Collection School Of Computing and Information Systems
Evolutionary algorithms, such as differential evolution, excel in solving real-parameter optimization challenges. However, the effectiveness of a single algorithm varies across different problem instances, necessitating considerable efforts in algorithm selection or configuration. This article aims to address the limitation by leveraging the complementary strengths of a group of algorithms and dynamically scheduling them throughout the optimization progress for specific problems. We propose a deep reinforcement learning-based dynamic algorithm selection framework to accomplish this task. Our approach models the dynamic algorithm selection a Markov decision process, training an agent in a policy gradient manner to select the most suitable algorithm according …
Hop‑Based Heterogeneous Graph Transformer, Zixuan Yang, Xiao Wang, Yanhua Yu, Yuling Wang, Kangkang Lu, Zirui Guo, Xiting Qin, Yunshan Ma, Tat‑Seng Chua
Hop‑Based Heterogeneous Graph Transformer, Zixuan Yang, Xiao Wang, Yanhua Yu, Yuling Wang, Kangkang Lu, Zirui Guo, Xiting Qin, Yunshan Ma, Tat‑Seng Chua
Research Collection School Of Computing and Information Systems
The Graph Transformer (GT) has shown significant ability in processing graph-structured data, addressing limitations in graph neural networks, such as over-smoothing and over-squashing. However, the implementation of GT in real-world heterogeneous graphs (HGs) with complex topology continues to present numerous challenges. Firstly, a challenge arises in designing a tokenizer that is compatible with heterogeneity. Secondly, the complexity of the transformer hampers the acquisition of high-order neighbor information in HGs. In this paper, we propose a novel Hop-basedHeterogeneous Graph Transformer (H2Gormer) framework, paving a promising path for HGs to benefit from the capabilities of Transformers. We propose a Heterogeneous Hop-based Token …
Active Discovering New Slots For Task-Oriented Conversation, Yuxia Wu, Tianhao Dai, Zhedong Zheng, Lizi Liao
Active Discovering New Slots For Task-Oriented Conversation, Yuxia Wu, Tianhao Dai, Zhedong Zheng, Lizi Liao
Research Collection School Of Computing and Information Systems
Existing task-oriented conversational systems heavily rely on domain ontologies with pre-defined slots and candidate values. In practical settings, these prerequisites are hard to meet, due to the emerging new user requirements and ever-changing scenarios. To mitigate these issues for better interaction performance, there are efforts working towards detecting out-of-vocabulary values or discovering new slots under unsupervised or semi-supervised learning paradigms. However, overemphasizing on the conversation data patterns alone induces these methods to yield noisy and arbitrary slot results. To facilitate the pragmatic utility, real-world systems tend to provide a stringent amount of human labeling quota, which offers an authoritative way …
T-Pickseer: Visual Analysis Of Taxi Pick-Up Point Selection Behavior, Shuxian Gu, Yemo Dai, Zezheng Feng, Yong Wang, Haipeng Zeng
T-Pickseer: Visual Analysis Of Taxi Pick-Up Point Selection Behavior, Shuxian Gu, Yemo Dai, Zezheng Feng, Yong Wang, Haipeng Zeng
Research Collection School Of Computing and Information Systems
Taxi drivers often take much time to navigate the streets to look for passengers, which leads to high vacancy rates and wasted resources. Empty taxi cruising remains a big concern for taxi companies. Analyzing the pick-up point selection behavior can solve this problem effectively, providing suggestions for taxi management and dispatch. Many studies have been devoted to analyzing and recommending hotspot regions of pick-up points, which can make it easier for drivers to pick-up passengers. However, the selection of pick-up points is complex and affected by multiple factors, such as convenience and traffic management. Most existing approaches cannot produce satisfactory …
Harnessing The Advances Of Meda To Optimize Multi-Puf For Enhancing Ip Security Of Biochips, Chen Dong, Xiaodong Guo, Sihuang Lian, Yinan Yao, Zhenyi Chen, Yang Yang, Zhanghui Liu
Harnessing The Advances Of Meda To Optimize Multi-Puf For Enhancing Ip Security Of Biochips, Chen Dong, Xiaodong Guo, Sihuang Lian, Yinan Yao, Zhenyi Chen, Yang Yang, Zhanghui Liu
Research Collection School Of Computing and Information Systems
Digital microfluidic biochips (DMFBs) have a significant stride in the applications of medicine and the biochemistry in recent years. DMFBs based on micro-electrode-dot-array (MEDA) architecture, as the next-generation DMFBs, aim to overcome drawbacks of conventional DMFBs, such as droplet size restriction, low accuracy, and poor sensing ability. Since the potential market value of MEDA biochips is vast, it is of paramount importance to explore approaches to protect the intellectual property (IP) of MEDA biochips during the development process. In this paper, an IP authentication strategy based on the multi-PUF applied to MEDA biochips is presented, called bioMPUF, consisting of Delay …
Knowledge Generation For Zero-Shot Knowledge-Based Vqa, Rui Cao, Jing Jiang
Knowledge Generation For Zero-Shot Knowledge-Based Vqa, Rui Cao, Jing Jiang
Research Collection School Of Computing and Information Systems
Previous solutions to knowledge-based visual question answering (K-VQA) retrieve knowledge from external knowledge bases and use supervised learning to train the K-VQA model. Recently pre-trained LLMs have been used as both a knowledge source and a zero-shot QA model for K-VQA and demonstrated promising results. However, these recent methods do not explicitly show the knowledge needed to answer the questions and thus lack interpretability. Inspired by recent work on knowledge generation from LLMs for text-based QA, in this work we propose and test a similar knowledge-generation-based K-VQA method, which first generates knowledge from an LLM and then incorporates the generated …
Conditional Neural Heuristic For Multiobjective Vehicle Routing Problems, Mingfeng Fan, Yaoxin Wu, Zhiguang Cao, Wen Song, Guillaume Sartoretti, Huan Liu, Guohua Wu
Conditional Neural Heuristic For Multiobjective Vehicle Routing Problems, Mingfeng Fan, Yaoxin Wu, Zhiguang Cao, Wen Song, Guillaume Sartoretti, Huan Liu, Guohua Wu
Research Collection School Of Computing and Information Systems
Existing neural heuristics for multiobjective vehicle routing problems (MOVRPs) are primarily conditioned on instance context, which failed to appropriately exploit preference and problem size, thus holding back the performance. To thoroughly unleash the potential, we propose a novel conditional neural heuristic (CNH) that fully leverages the instance context, preference, and size with an encoder–decoder structured policy network. Particularly, in our CNH, we design a dual-attention-based encoder to relate preferences and instance contexts, so as to better capture their joint effect on approximating the exact Pareto front (PF). We also design a size-aware decoder based on the sinusoidal encoding to explicitly …
Temporal Implicit Multimodal Networks For Investment And Risk Management, Meng Kiat Gary Ang, Ee-Peng Lim
Temporal Implicit Multimodal Networks For Investment And Risk Management, Meng Kiat Gary Ang, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
Many deep learning works on financial time-series forecasting focus on predicting future prices/returns of individual assets with numerical price-related information for trading, and hence propose models designed for univariate, single-task, and/or unimodal settings. Forecasting for investment and risk management involves multiple tasks in multivariate settings: forecasts of expected returns and risks of assets in portfolios, and correlations between these assets. As different sources/types of time-series influence future returns, risks, and correlations of assets in different ways, it is also important to capture time-series from different modalities. Hence, this article addresses financial time-series forecasting for investment and risk management in a …
T-Sciq: Teaching Multimodal Chain-Of-Thought Reasoning Via Large Language Model Signals For Science Question Answering, Lei Wang, Yi Hu, Jiabang He, Xing Xu, Ning Liu, Hui Liu, Heng Tao Shen
T-Sciq: Teaching Multimodal Chain-Of-Thought Reasoning Via Large Language Model Signals For Science Question Answering, Lei Wang, Yi Hu, Jiabang He, Xing Xu, Ning Liu, Hui Liu, Heng Tao Shen
Research Collection School Of Computing and Information Systems
Large Language Models (LLMs) have recently demonstrated exceptional performance in various Natural Language Processing (NLP) tasks. They have also shown the ability to perform chain-of-thought (CoT) reasoning to solve complex problems. Recent studies have explored CoT reasoning in complex multimodal scenarios, such as the science question answering task, by fine-tuning multimodal models with high-quality human-annotated CoT rationales. However, collecting high-quality COT rationales is usually time-consuming and costly. Besides, the annotated rationales are hardly accurate due to the external essential information missed. To address these issues, we propose a novel method termed T-SciQ that aims at teaching science question answering with …
Simulated Annealing With Reinforcement Learning For The Set Team Orienteering Problem With Time Windows, Vincent F. Yu, Nabila Y. Salsabila, Shih-W Lin, Aldy Gunawan
Simulated Annealing With Reinforcement Learning For The Set Team Orienteering Problem With Time Windows, Vincent F. Yu, Nabila Y. Salsabila, Shih-W Lin, Aldy Gunawan
Research Collection School Of Computing and Information Systems
This research investigates the Set Team Orienteering Problem with Time Windows (STOPTW), a new variant of the well-known Team Orienteering Problem with Time Windows and Set Orienteering Problem. In the STOPTW, customers are grouped into clusters. Each cluster is associated with a profit attainable when a customer in the cluster is visited within the customer's time window. A Mixed Integer Linear Programming model is formulated for STOPTW to maximizing total profit while adhering to time window constraints. Since STOPTW is an NP-hard problem, a Simulated Annealing with Reinforcement Learning (SARL) algorithm is developed. The proposed SARL incorporates the core concepts …
Community Similarity Based On User Profile Joins, Konstantinos Theocharidis, Hady Wirawan Lauw
Community Similarity Based On User Profile Joins, Konstantinos Theocharidis, Hady Wirawan Lauw
Research Collection School Of Computing and Information Systems
Similarity joins on multidimensional data are crucial operators for recommendation purposes. The classic ��-join problem finds all pairs of points within �� distance to each other among two ��-dimensional datasets. In this paper, we consider a novel and alternative version of ��-join named community similarity based on user profile joins (CSJ). The aim of CSJ problem is, given two communities having a set of ��-dimensional users, to find how similar are the communities by matching every single pair of users (a user can be matched with at most one other user) having an absolute difference of at most �� per …
Improvement Of Flow Coefficient Estimation With Limited Well Test Data For Real-Time Condition Analytics Of Choke Valve, T. Visawameteekul, Tin Seong Kam, P. Thamvechvitee
Improvement Of Flow Coefficient Estimation With Limited Well Test Data For Real-Time Condition Analytics Of Choke Valve, T. Visawameteekul, Tin Seong Kam, P. Thamvechvitee
Research Collection School Of Computing and Information Systems
The study discusses a method for monitoring the internal condition of choke valves to predict sand erosion using flow coefficient (Cv). The method calculates the Cv of the choke valve by utilizing eight parameters and compares it to the newly manufactured value to generate warnings. However, the availability of spot-check well test data can significantly impact the model's efficiency if tests are performed infrequently. To address this issue, the Extended Cv monitoring method is proposed in this paper. The main purpose of this study is to develop a model for estimating Cv value in the absence of well test data. …
Stopguess: A Framework For Public-Key Authenticated Encryption With Keyword Search, Tao Xiang, Zhongming Wang, Biwen Chen, Xiaoguo Li, Peng Wang, Fei Chen
Stopguess: A Framework For Public-Key Authenticated Encryption With Keyword Search, Tao Xiang, Zhongming Wang, Biwen Chen, Xiaoguo Li, Peng Wang, Fei Chen
Research Collection School Of Computing and Information Systems
Public key encryption with keyword search (PEKS) allows users to search on encrypted data without leaking the keyword information from the ciphertexts. But it does not preserve keyword privacy within the trapdoors, because an adversary (e.g., untrusted server) might launch inside keyword-guessing attacks (IKGA) to guess keywords from the trapdoors. In recent years, public key authenticated encryption with keyword search (PAEKS) has become a promising primitive to counter the IKGA. However, existing PAEKS schemes focus on the concrete construction of PAEKS, making them unable to support modular construction, intuitive proof, or flexible extension. In this paper, our proposal called “StopGuess” …
On The Effects Of Information Asymmetry In Digital Currency Trading, Kwansoo Kim, Robert John Kauffman
On The Effects Of Information Asymmetry In Digital Currency Trading, Kwansoo Kim, Robert John Kauffman
Research Collection School Of Computing and Information Systems
We report on two studies that examine how social sentiment influences information asymmetry in digital currency markets. We also assess whether cryptocurrency can be an investment vehicle, as opposed to only an instrument for asset speculation. Using a dataset on transactions from an exchange in South Korea and sentiment from Korean social media in 2018, we conducted a study of different trading behavior under two cryptocurrency trading market microstructures: a bid-ask spread dealer's market and a continuous trading buy-sell, immediate trade execution market. Our results highlight the impacts of positive and negative trader social sentiment valences on the effects of …
Multiobjective Stochastic Optimization: A Case Of Real-Time Matching In Ride-Sourcing Markets, Guodong Lyu, Wang Chi Cheung, Chung-Piaw Teo, Hai Wang
Multiobjective Stochastic Optimization: A Case Of Real-Time Matching In Ride-Sourcing Markets, Guodong Lyu, Wang Chi Cheung, Chung-Piaw Teo, Hai Wang
Research Collection School Of Computing and Information Systems
Problem Definition: The job of any marketplace is to facilitate the matching of supply with demand in real-time. Success is often measured using various metrics. The challenge is to design matching algorithms to balance the trade-offs among multiple objectives in a stochastic environment, to arrive at a “compromise” solution, which minimizes say the ℓp-norm-based distance function (for some 1 ≤p ≤∞) between the attained performance metrics and the target performances.Methodology/Results: We observe that the sample-average-approximation formulation of this multi-objective stochastic optimization problem can be solved by an online algorithm that uses only gradient information from “historical” (i.e., past) sample information, …
Screening Through A Broad Pool: Towards Better Diversity For Lexically Constrained Text Generation, Changsen Yuan, Heyan Huang, Yixin Cao, Qianwen Cao
Screening Through A Broad Pool: Towards Better Diversity For Lexically Constrained Text Generation, Changsen Yuan, Heyan Huang, Yixin Cao, Qianwen Cao
Research Collection School Of Computing and Information Systems
Lexically constrained text generation (CTG) is to generate text that contains given constrained keywords. However, the text diversity of existing models is still unsatisfactory. In this paper, we propose a lightweight dynamic refinement strategy that aims at increasing the randomness of inference to improve generation richness and diversity while maintaining a high level of fluidity and integrity. Our basic idea is to enlarge the number and length of candidate sentences in each iteration, and choose the best for subsequent refinement. On the one hand, different from previous works, which carefully insert one token between two words per action, we insert …
Non-Binary Evaluation Of Next-Basket Food Recommendation, Yue Liu, Palakorn Achananuparp, Ee-Peng Lim
Non-Binary Evaluation Of Next-Basket Food Recommendation, Yue Liu, Palakorn Achananuparp, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
Next-basket recommendation (NBR) is a recommendation task that predicts a basket or a set of items a user is likely to adopt next based on his/her history of basket adoption sequences. It enables a wide range of novel applications and services from predicting next basket of items for grocery shopping to recommending food items a user is likely to consume together in the next meal. Even though much progress has been made in the algorithmic NBR research over the years, little research has been done to broaden knowledge about the evaluation of NBR methods, which is largely based on the …
Test-Time Augmentation For 3d Point Cloud Classification And Segmentation, Tuan-Anh Vu, Srinjay Sarkar, Zhiyuan Zhang, Binh-Son Hua, Sai-Kit Yeung
Test-Time Augmentation For 3d Point Cloud Classification And Segmentation, Tuan-Anh Vu, Srinjay Sarkar, Zhiyuan Zhang, Binh-Son Hua, Sai-Kit Yeung
Research Collection School Of Computing and Information Systems
Data augmentation is a powerful technique to enhance the performance of a deep learning task but has received less attention in 3D deep learning. It is well known that when 3D shapes are sparsely represented with low point density, the performance of the downstream tasks drops significantly. This work explores test-time augmentation (TTA) for 3D point clouds. We are inspired by the recent revolution of learning implicit representation and point cloud upsampling, which can produce high-quality 3D surface reconstruction and proximity-to-surface, respectively. Our idea is to leverage the implicit field reconstruction or point cloud upsampling techniques as a systematic way …
Iterative Graph Self-Distillation, Hanlin Zhang, Shuai Lin, Weiyang Liu, Pan Zhou, Jian Tang, Xiaodan Liang, Eric Xing
Iterative Graph Self-Distillation, Hanlin Zhang, Shuai Lin, Weiyang Liu, Pan Zhou, Jian Tang, Xiaodan Liang, Eric Xing
Research Collection School Of Computing and Information Systems
Recently, there has been increasing interest in the challenge of how to discriminatively vectorize graphs. To address this, we propose a method called Iterative Graph Self-Distillation (IGSD) which learns graph-level representation in an unsupervised manner through instance discrimination using a self-supervised contrastive learning approach. IGSD involves a teacher-student distillation process that uses graph diffusion augmentations and constructs the teacher model using an exponential moving average of the student model. The intuition behind IGSD is to predict the teacher network representation of the graph pairs under different augmented views. As a natural extension, we also apply IGSD to semi-supervised scenarios by …
Towards Understanding Convergence And Generalization Of Adamw, Pan Zhou, Xingyu Xie, Zhouchen Lin, Shuicheng Yan
Towards Understanding Convergence And Generalization Of Adamw, Pan Zhou, Xingyu Xie, Zhouchen Lin, Shuicheng Yan
Research Collection School Of Computing and Information Systems
AdamW modifies Adam by adding a decoupled weight decay to decay network weights per training iteration. For adaptive algorithms, this decoupled weight decay does not affect specific optimization steps, and differs from the widely used ℓ2-regularizer which changes optimization steps via changing the first- and second-order gradient moments. Despite its great practical success, for AdamW, its convergence behavior and generalization improvement over Adam and ℓ2-regularized Adam (ℓ2-Adam) remain absent yet. To solve this issue, we prove the convergence of AdamW and justify its generalization advantages over Adam and ℓ2-Adam. Specifically, AdamW provably converges but minimizes a dynamically regularized loss that …
Attack As Detection: Using Adversarial Attack Methods To Detect Abnormal Examples, Zhe Zhao, Guangke Chen, Tong Liu, Taishan Li, Fu Song, Jingyi Wang, Jun Sun
Attack As Detection: Using Adversarial Attack Methods To Detect Abnormal Examples, Zhe Zhao, Guangke Chen, Tong Liu, Taishan Li, Fu Song, Jingyi Wang, Jun Sun
Research Collection School Of Computing and Information Systems
As a new programming paradigm, deep learning (DL) has achieved impressive performance in areas such as image processing and speech recognition, and has expanded its application to solve many real-world problems. However, neural networks and DL are normally black-box systems; even worse, DL-based software are vulnerable to threats from abnormal examples, such as adversarial and backdoored examples constructed by attackers with malicious intentions as well as unintentionally mislabeled samples. Therefore, it is important and urgent to detect such abnormal examples. Although various detection approaches have been proposed respectively addressing some specific types of abnormal examples, they suffer from some limitations; …
Self-Admitted Technical Debts Identification: How Far Are We?, Hao Gu, Shichao Zhang, Qiao Huang, Zhifang Liao, Jiakun Liu, David Lo
Self-Admitted Technical Debts Identification: How Far Are We?, Hao Gu, Shichao Zhang, Qiao Huang, Zhifang Liao, Jiakun Liu, David Lo
Research Collection School Of Computing and Information Systems
Self-admitted technical debt (SATD) is a kind of technical debt that is already acknowledged by the developers and needs additional work or resources to address in the future. In recent years, though many methods have been proposed to detect SATDs, these methods have mainly focused on Java-type code comments published by Maldonado et al. It is unclear whether these methods trained on Maldonado's code comments dataset can find SATD in other programming languages or other software artifacts, such as issue trackers, pull requests, and commit messages effectively. In order to answer the above confusion and investigate how far our community …
Sustainability Forecasting For Deep Learning Packages, Junxiao Han, Yunkun Wang, Zhongxin Liu, Lingfeng Bao, Jiakun Liu, David Lo, Shuiguang Deng
Sustainability Forecasting For Deep Learning Packages, Junxiao Han, Yunkun Wang, Zhongxin Liu, Lingfeng Bao, Jiakun Liu, David Lo, Shuiguang Deng
Research Collection School Of Computing and Information Systems
Deep Learning (DL) technologies have been widely adopted to tackle various tasks. In this process, through software dependencies, a multi-layer DL supply chain (SC) is formed, with DL frameworks acting as the root, DL packages acting as the bridge nodes, and downstream DL projects acting as the periphery. However, most Open Source Software (OSS) projects may fail. Considering the crucial position of DL packages in the DL SC, to foster the sustainable development of DL SCs and DL packages, we aim to forecast the long-term sustainability of DL packages. Here, sustained activity is adopted as the main proxy of sustainability, …
Leveraging Multimodal Features And Item‑Level User Feedback For Bundle Construction, Yunshan Ma, Xiaohao Liu, Yinwei Wei, Zhulin Tao, Xiang Wang, Tat‑Seng Chua
Leveraging Multimodal Features And Item‑Level User Feedback For Bundle Construction, Yunshan Ma, Xiaohao Liu, Yinwei Wei, Zhulin Tao, Xiang Wang, Tat‑Seng Chua
Research Collection School Of Computing and Information Systems
Automatic bundle construction is a crucial prerequisite step in various bundle-aware online services. Previous approaches are mostly designed to model the bundling strategy of existing bundles. However, it is hard to acquire large-scale well-curated bundle dataset, especially for those platforms that have not offered bundle services before. Even for platforms with mature bundle services, there are still many items that are included in few or even zero bundles, which give rise to sparsity and cold-start challenges in the bundle construction models. To tackle these issues, we target at leveraging multimodal features, item-level user feedback signals, and the bundle composition information, …
Faster Rates For Compressed Federated Learning With Client-Variance Reduction, Haoyu Zhao, Konstantin Burlachenko, Zhize Li, Peter Richtarik
Faster Rates For Compressed Federated Learning With Client-Variance Reduction, Haoyu Zhao, Konstantin Burlachenko, Zhize Li, Peter Richtarik
Research Collection School Of Computing and Information Systems
Due to the communication bottleneck in distributed and federated learning applications, algorithms using communication compression have attracted significant attention and are widely used in practice. Moreover, the huge number, high heterogeneity, and limited availability of clients result in high client -variance. This paper addresses these two issues together by proposing compressed and clientvariance reduced methods COFIG and FRECON. We prove an O( (1+\omega)3/2\surdN+ (1+\omega)N2/3 S\epsilon2 S\epsilon2 ) bound on the number of communication rounds of COFIG in the nonconvex setting, where N is the total number of clients, S is the number of clients participating in each round, \epsilon is …
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 …
Ditmos: Delving Into Diverse Tiny-Model Selection On Microcontrollers, Xiao Ma, Shengfeng He, Hezhe Qiao, Dong Ma
Ditmos: Delving Into Diverse Tiny-Model Selection On Microcontrollers, Xiao Ma, Shengfeng He, Hezhe Qiao, Dong Ma
Research Collection School Of Computing and Information Systems
Enabling efficient and accurate deep neural network (DNN) inference on microcontrollers is non-trivial due to the constrained on-chip resources. Current methodologies primarily focus on compressing larger models yet at the expense of model accuracy. In this paper, we rethink the problem from the inverse perspective by constructing small/weak models directly and improving their accuracy. Thus, we introduce DiTMoS, a novel DNN training and inference framework with a selectorclassifiers architecture, where the selector routes each input sample to the appropriate classifier for classification. DiTMoS is grounded on a key insight: a composition of weak models can exhibit high diversity and the …
Win: Weight-Decay-Integrated Nesterov Acceleration For Faster Network Training, Pan Zhou, Xingyu Xie, Zhouchen Lin, Kim-Chuan Toh, Shuicheng Yan
Win: Weight-Decay-Integrated Nesterov Acceleration For Faster Network Training, Pan Zhou, Xingyu Xie, Zhouchen Lin, Kim-Chuan Toh, Shuicheng Yan
Research Collection School Of Computing and Information Systems
Training deep networks on large-scale datasets is computationally challenging. This work explores the problem of “how to accelerate adaptive gradient algorithms in a general manner", and proposes an effective Weight-decay-Integrated Nesterov acceleration (Win) to accelerate adaptive algorithms. Taking AdamW and Adam as examples, per iteration, we construct a dynamical loss that combines the vanilla training loss and a dynamic regularizer inspired by proximal point method, and respectively minimize the first- and second-order Taylor approximations of dynamical loss to update variable. This yields our Win acceleration that uses a conservative step and an aggressive step to update, and linearly combines these …