no code implementations • 12 Sep 2017 • Huijun Wu, Chen Wang, Jie Yin, Kai Lu, Liming Zhu
In this paper, we propose a method to disclose a small set of training data that is just sufficient for users to get the insight of a complicated model.
2 code implementations • 13 Feb 2018 • Shuai Zhang, Lina Yao, Yi Tay, Xiwei Xu, Xiang Zhang, Liming Zhu
In the past decade, matrix factorization has been extensively researched and has become one of the most popular techniques for personalized recommendations.
2 code implementations • 5 Mar 2019 • Huijun Wu, Chen Wang, Yuriy Tyshetskiy, Andrew Docherty, Kai Lu, Liming Zhu
Based on this observation, we propose a defense approach which inspects the graph and recovers the potential adversarial perturbations.
1 code implementation • 1 Mar 2020 • Jieshan Chen, Chunyang Chen, Zhenchang Xing, Xiwei Xu, Liming Zhu, Guoqiang Li, Jinshui Wang
However, the prerequisite of using screen readers is that developers have to add natural-language labels to the image-based components when they are developing the app.
no code implementations • 8 Apr 2020 • Manqing Dong, Feng Yuan, Lina Yao, Xianzhi Wang, Xiwei Xu, Liming Zhu
A significant remaining challenge for existing recommender systems is that users may not trust the recommender systems for either lack of explanation or inaccurate recommendation results.
1 code implementation • 7 Jul 2020 • Manqing Dong, Feng Yuan, Lina Yao, Xiwei Xu, Liming Zhu
However, most meta-learning based recommendation approaches adopt model-agnostic meta-learning for parameter initialization, where the global sharing parameter may lead the model into local optima for some users.
no code implementations • 22 Jul 2020 • Sin Kit Lo, Qinghua Lu, Chen Wang, Hye-Young Paik, Liming Zhu
Federated learning is an emerging machine learning paradigm where clients train models locally and formulate a global model based on the local model updates.
2 code implementations • 12 Aug 2020 • Jieshan Chen, Mulong Xie, Zhenchang Xing, Chunyang Chen, Xiwei Xu, Liming Zhu, Guoqiang Li
We conduct the first large-scale empirical study of seven representative GUI element detection methods on over 50k GUI images to understand the capabilities, limitations and effective designs of these methods.
no code implementations • 6 Sep 2020 • Weishan Zhang, Qinghua Lu, Qiuyu Yu, Zhaotong Li, Yue Liu, Sin Kit Lo, Shiping Chen, Xiwei Xu, Liming Zhu
Therefore, in this paper, we present a platform architecture of blockchain-based federated learning systems for failure detection in IIoT.
2 code implementations • 13 Oct 2020 • Sunny Verma, Chen Wang, Liming Zhu, Wei Liu
The principal component analysis network (PCANet) is an unsupervised parsimonious deep network, utilizing principal components as filters in its convolution layers.
no code implementations • 4 Nov 2020 • Xiaocong Chen, Lina Yao, Aixin Sun, Xianzhi Wang, Xiwei Xu, Liming Zhu
Deep reinforcement learning uses a reward function to learn user's interest and to control the learning process.
no code implementations • 1 Jan 2021 • Manqing Dong, Lina Yao, Xianzhi Wang, Xiwei Xu, Liming Zhu
A key challenge for meta-optimization based approaches is to determine whether an initialization condition can be generalized to tasks with diverse distributions to accelerate learning.
no code implementations • 5 Jan 2021 • Jiamou Sun, Zhenchang Xing, Hao Guo, Deheng Ye, Xiaohong Li, Xiwei Xu, Liming Zhu
The extracted aspects from an ExploitDB post are then composed into a CVE description according to the suggested CVE description templates, which is must-provided information for requesting new CVEs.
no code implementations • 7 Jan 2021 • Sin Kit Lo, Qinghua Lu, Liming Zhu, Hye-Young Paik, Xiwei Xu, Chen Wang
Therefore, in this paper, we present a collection of architectural patterns to deal with the design challenges of federated learning systems.
no code implementations • 19 May 2021 • Liming Zhu, Xiwei Xu, Qinghua Lu, Guido Governatori, Jon Whittle
In the last few years, AI continues demonstrating its positive impact on society while sometimes with ethically questionable consequences.
no code implementations • 22 Jun 2021 • Sin Kit Lo, Qinghua Lu, Hye-Young Paik, Liming Zhu
The proposed FLRA reference architecture is based on an extensive review of existing patterns of federated learning systems found in the literature and existing industrial implementation.
no code implementations • 16 Aug 2021 • Sin Kit Lo, Yue Liu, Qinghua Lu, Chen Wang, Xiwei Xu, Hye-Young Paik, Liming Zhu
To enhance the accountability and fairness of federated learning systems, we present a blockchain-based trustworthy federated learning architecture.
no code implementations • 29 Sep 2021 • Haiyan Zhao, Tianyi Zhou, Guodong Long, Jing Jiang, Liming Zhu, Chengqi Zhang
Can we find a better initialization for a new task, e. g., a much smaller network closer to the final pruned model, by exploiting its similar tasks?
1 code implementation • 29 Oct 2021 • Guanglin Zhou, Lina Yao, Xiwei Xu, Chen Wang, Liming Zhu
With the widespread accumulation of observational data, researchers obtain a new direction to learn counterfactual effects in many domains (e. g., health care and computational advertising) without Randomized Controlled Trials(RCTs).
no code implementations • 18 Nov 2021 • Qinghua Lu, Liming Zhu, Xiwei Xu, Jon Whittle, David Douglas, Conrad Sanderson
These patterns provide concrete, operationalised guidance that facilitate the development of responsible AI systems.
1 code implementation • NeurIPS 2021 • Shuang Ao, Tianyi Zhou, Guodong Long, Qinghua Lu, Liming Zhu, Jing Jiang
Next, a bottom-up traversal of the tree trains the RL agent from easier sub-tasks with denser rewards on bottom layers to harder ones on top layers and collects its cost on each sub-task train the planner in the next episode.
no code implementations • 2 Mar 2022 • Qinghua Lu, Liming Zhu, Xiwei Xu, Jon Whittle
In the meantime much effort has been put into responsible AI from the algorithm perspective, but they are limited to a small subset of ethical principles amenable to mathematical analysis.
no code implementations • 9 Mar 2022 • Qinghua Lu, Liming Zhu, Xiwei Xu, Jon Whittle, Zhenchang Xing
Although AI is transforming the world, there are serious concerns about its ability to behave and make decisions responsibly.
no code implementations • 28 Apr 2022 • Sin Kit Lo, Qinghua Lu, Hye-Young Paik, Liming Zhu
Federated machine learning is growing fast in academia and industries as a solution to solve data hungriness and privacy issues in machine learning.
1 code implementation • 15 Jun 2022 • Mulong Xie, Zhenchang Xing, Sidong Feng, Chunyang Chen, Liming Zhu, Xiwei Xu
These principles are domain-independent and have been widely adopted by practitioners to structure content on GUIs to improve aesthetic pleasant and usability.
no code implementations • 13 Aug 2022 • Guanglin Zhou, Lina Yao, Xiwei Xu, Chen Wang, Liming Zhu
We regularly consider answering counterfactual questions in practice, such as "Would people with diabetes take a turn for the better had they choose another medication?".
no code implementations • 13 Aug 2022 • Guanglin Zhou, Chengkai Huang, Xiaocong Chen, Xiwei Xu, Chen Wang, Liming Zhu, Lina Yao
Recognizing that confounders may be elusive, we propose a contrastive self-supervised learning to minimize exposure bias, employing inverse propensity scores and expanding the positive sample set.
no code implementations • 12 Sep 2022 • Qinghua Lu, Liming Zhu, Xiwei Xu, Jon Whittle, Didar Zowghi, Aurelie Jacquet
Rather than staying at the principle or algorithm level, we focus on patterns that AI system stakeholders can undertake in practice to ensure that the developed AI systems are responsible throughout the entire governance and engineering lifecycle.
no code implementations • 3 Jan 2023 • Qinghua Lu, Yuxiu Luo, Liming Zhu, Mingjian Tang, Xiwei Xu, Jon Whittle
In this article, we first summarise the major challenges in operationalising responsible AI at scale and introduce how we use the Responsible AI Pattern Catalogue to address those challenges.
no code implementations • 29 Jan 2023 • Guanglin Zhou, Shaoan Xie, GuangYuan Hao, Shiming Chen, Biwei Huang, Xiwei Xu, Chen Wang, Liming Zhu, Lina Yao, Kun Zhang
In the field of artificial intelligence (AI), the quest to understand and model data-generating processes (DGPs) is of paramount importance.
no code implementations • 7 Feb 2023 • Dawen Zhang, Shidong Pan, Thong Hoang, Zhenchang Xing, Mark Staples, Xiwei Xu, Lina Yao, Qinghua Lu, Liming Zhu
The right to be forgotten (RTBF) is motivated by the desire of people not to be perpetually disadvantaged by their past deeds.
no code implementations • 12 Mar 2023 • Linh T. Nguyen, Lam Duc Nguyen, Thong Hoang, Dilum Bandara, Qin Wang, Qinghua Lu, Xiwei Xu, Liming Zhu, Petar Popovski, Shiping Chen
Second, we focus on the convergence of blockchain and data sharing to give a clear picture of this landscape and propose a reference architecture for blockchain-based data sharing.
no code implementations • 13 Apr 2023 • Qinghua Lu, Liming Zhu, Xiwei Xu, Zhenchang Xing, Jon Whittle
The release of ChatGPT has drawn huge interests on foundations models.
no code implementations • 9 May 2023 • Qinghua Lu, Liming Zhu, Xiwei Xu, Yue Liu, Zhenchang Xing, Jon Whittle
The recent release of large language model (LLM) based chatbots, such as ChatGPT, has attracted huge interest in foundation models.
no code implementations • 25 May 2023 • Sin Kit Lo, Yue Liu, Guangsheng Yu, Qinghua Lu, Xiwei Xu, Liming Zhu
Distributed trust is a nebulous concept that has evolved from different perspectives in recent years.
no code implementations • 11 Aug 2023 • Yue Liu, Qinghua Lu, Liming Zhu, Hye-Young Paik
Foundation models including large language models (LLMs) are increasingly attracting interest worldwide for their distinguished capabilities and potential to perform a wide variety of tasks.
no code implementations • 14 Sep 2023 • Terry Yue Zhuo, Xiaoning Du, Zhenchang Xing, Jiamou Sun, Haowei Quan, Li Li, Liming Zhu
The correctness and unambiguity of API usage among these code models are crucial for achieving desirable program functionalities, requiring them to learn various API fully qualified names structurally and semantically.
no code implementations • 8 Nov 2023 • Yashothara Shanmugarasa, M. A. P. Chamikara, Hye-Young Paik, Salil S. Kanhere, Liming Zhu
In this paper, we propose a novel LDP approach (named LDP-SmartEnergy) that utilizes randomized response techniques with sliding windows to facilitate the sharing of appliance-level energy consumption data over time while not revealing individual users' appliance usage patterns.
no code implementations • 22 Nov 2023 • Qinghua Lu, Liming Zhu, Xiwei Xu, Zhenchang Xing, Stefan Harrer, Jon Whittle
Foundation models, such as large language models (LLMs), have been widely recognised as transformative AI technologies due to their capabilities to understand and generate content, including plans with reasoning capabilities.
no code implementations • 30 Nov 2023 • Dawen Zhang, Boming Xia, Yue Liu, Xiwei Xu, Thong Hoang, Zhenchang Xing, Mark Staples, Qinghua Lu, Liming Zhu
The advent of Generative AI has marked a significant milestone in artificial intelligence, demonstrating remarkable capabilities in generating realistic images, texts, and data patterns.
no code implementations • 18 Jan 2024 • Guanglin Zhou, Zhongyi Han, Shiming Chen, Biwei Huang, Liming Zhu, Tongliang Liu, Lina Yao, Kun Zhang
Domain Generalization (DG) endeavors to create machine learning models that excel in unseen scenarios by learning invariant features.
no code implementations • 11 Feb 2024 • Zhibo Hu, Chen Wang, Yanfeng Shu, Helen, Paik, Liming Zhu
In this work, we find that the insertion of even a short prefix to the prompt leads to the generation of outputs far away from factually correct answers.
no code implementations • 14 Feb 2024 • Shiyi Yang, Lina Yao, Chen Wang, Xiwei Xu, Liming Zhu
Recent studies have shown that recommender systems (RSs) are highly vulnerable to data poisoning attacks.