Recent emergence of multilingual pre-training language model (mPLM) has enabled breakthroughs on various downstream cross-lingual transfer (CLT) tasks.
When building models for novel natural language domains, a major challenge is the lack of data in the new domains, no matter whether the data is annotated or not.
Sports game summarization aims to generate news articles from live text commentaries.
Federated learning models must be protected against plagiarism since these models are built upon valuable training data owned by multiple institutions or people. This paper illustrates a novel federated deep neural network (FedDNN) ownership verification scheme that allows ownership signatures to be embedded and verified to claim legitimate intellectual property rights (IPR) of FedDNN models, in case that models are illegally copied, re-distributed or misused.
To address the aforementioned perplexity, we propose a novel Bayesian Privacy (BP) framework which enables Bayesian restoration attacks to be formulated as the probability of reconstructing private data from observed public information.
We study the problem of query attribute value extraction, which aims to identify named entities from user queries as diverse surface form attribute values and afterward transform them into formally canonical forms.
Federated masked matrix factorization could protect the data privacy in federated recommender systems without sacrificing efficiency or efficacy.
Experiments on both synthetic and real-world datasets show the framework to be highly effective at detection in both multilingual data and in languages where training samples are scarce.
Data-driven approaches have been applied to many problems in urban computing.
Ever since Machine Learning as a Service emerges as a viable business that utilizes deep learning models to generate lucrative revenue, Intellectual Property Right (IPR) has become a major concern because these deep learning models can easily be replicated, shared, and re-distributed by any unauthorized third parties.
Transferability estimation has been an essential tool in selecting a pre-trained model and the layers of it to transfer, so as to maximize the performance on a target task and prevent negative transfer.
This paper proposes a novel ternary hash encoding for learning to hash methods, which provides a principled more efficient coding scheme with performances better than those of the state-of-the-art binary hashing counterparts.
As artificial intelligence (AI)-empowered applications become widespread, there is growing awareness and concern for user privacy and data confidentiality.
Ever since Machine Learning as a Service (MLaaS) emerges as a viable business that utilizes deep learning models to generate lucrative revenue, Intellectual Property Right (IPR) has become a major concern because these deep learning models can easily be replicated, shared, and re-distributed by any unauthorized third parties.
Federated Learning (FL) provides both model performance and data privacy for machine learning tasks where samples or features are distributed among different parties.
To take advantage of the existing corpus, we propose a transfer learning model (dubbed as TrNews) for news recommendation to transfer the knowledge from a source corpus to a target corpus.
Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries.
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored.
As an innovative solution for privacy-preserving machine learning (ML), federated learning (FL) is attracting much attention from research and industry areas.
Existing research focuses on the recommendation performance of the target domain while ignores the privacy leakage of the source domain.
To systematically measure the effect of both white-box and black-box attacks, we propose a new metric to evaluate how transferable are the adversarial examples produced by a source model to a target model.
By and large, existing Intellectual Property (IP) protection on deep neural networks typically i) focus on image classification task only, and ii) follow a standard digital watermarking framework that was conventionally used to protect the ownership of multimedia and video content.
4 code implementations • 27 Jul 2020 • Chaoyang He, Songze Li, Jinhyun So, Xiao Zeng, Mi Zhang, Hongyi Wang, Xiaoyang Wang, Praneeth Vepakomma, Abhishek Singh, Hang Qiu, Xinghua Zhu, Jianzong Wang, Li Shen, Peilin Zhao, Yan Kang, Yang Liu, Ramesh Raskar, Qiang Yang, Murali Annavaram, Salman Avestimehr
Federated learning (FL) is a rapidly growing research field in machine learning.
Financial technology (FinTech) has been playing an increasingly critical role in driving modern economies, society, technology, and many other areas.
Matrix Factorization has been very successful in practical recommendation applications and e-commerce.
This paper investigates capabilities of Privacy-Preserving Deep Learning (PPDL) mechanisms against various forms of privacy attacks.
3 code implementations • 18 Jun 2020 • Qiang Yang, Hind Alamro, Somayah Albaradei, Adil Salhi, Xiaoting Lv, Changsheng Ma, Manal Alshehri, Inji Jaber, Faroug Tifratene, Wei Wang, Takashi Gojobori, Carlos M. Duarte, Xin Gao, Xiangliang Zhang
Since the first alert launched by the World Health Organization (5 January, 2020), COVID-19 has been spreading out to over 180 countries and territories.
In 5G and Beyond networks, Artificial Intelligence applications are expected to be increasingly ubiquitous.
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored.
As a result, the intra-field information and the non-linear interactions between those operations (e. g. neural network and factorization machines) are ignored.
Though the learned representations are separable in the source domain, they usually have a large variance and samples with different class labels tend to overlap in the target domain, which yields suboptimal adaptation performance.
Federated Learning (FL) proposed in recent years has received significant attention from researchers in that it can bring separate data sources together and build machine learning models in a collaborative but private manner.
Federated learning is a distributed machine learning framework which enables different parties to collaboratively train a model while protecting data privacy and security.
Federated learning (FL) is a promising approach to resolve this challenge.
We introduce a collaborative learning framework allowing multiple parties having different sets of attributes about the same user to jointly build models without exposing their raw data or model parameters.
6 code implementations • 10 Dec 2019 • Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Hubert Eichner, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaid Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konečný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, Ramesh Raskar, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches.
Our approach can considerably reduce the number of communication rounds with a little additional communication cost per round.
We propose to formulate multi-label learning as a estimation of class distribution in a non-linear embedding space, where for each label, its positive data embeddings and negative data embeddings distribute compactly to form a positive component and negative component respectively, while the positive component and negative component are pushed away from each other.
With this demonstration, the audience can experience the effect of LMA in an interactive and real-time fashion.
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem.
Modern Automatic Speech Recognition (ASR) systems primarily rely on scores from an Acoustic Model (AM) and a Language Model (LM) to rescore the N-best lists.
Federated learning is a new machine learning paradigm which allows data parties to build machine learning models collaboratively while keeping their data secure and private.
Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL models typically involves in a multi-step process: pre-training RL models on simulators, uploading the pre-trained model to real-life robots, and fine-tuning the weight parameters on robot vehicles.
Since the source and the target domains are usually from different distributions, existing methods mainly focus on adapting the cross-domain marginal or conditional distributions.
Ranked #5 on Domain Adaptation on ImageCLEF-DA
To verify the effectiveness of our approach, we conduct experiments on a real-world EEG dataset, consisting of heterogeneous data collected from diverse devices.
An effective content recommendation in modern social media platforms should benefit both creators to bring genuine benefits to them and consumers to help them get really interesting content.
To incorporate multiple relationships into spatial feature extraction, we define the problem as a multi-modal machine learning problem on multi-graph convolution networks.
Feature crossing captures interactions among categorical features and is useful to enhance learning from tabular data in real-world businesses.
In this paper, we propose a practically Easy Transfer Learning (EasyTL) approach which requires no model selection and hyperparameter tuning, while achieving competitive performance.
Ranked #3 on Transfer Learning on Office-Home
Under the condition that target labels are unknown, the key challenge of PDA is how to transfer relevant examples in the shared classes to promote positive transfer, and ignore irrelevant ones in the specific classes to mitigate negative transfer.
Ranked #3 on Partial Domain Adaptation on ImageNet-Caltech
We organized a competition on Autonomous Lifelong Machine Learning with Drift that was part of the competition program of NeurIPS 2018.
This federated learning system allows the learning process to be jointly conducted over multiple parties with common user samples but different feature sets, which corresponds to a vertically partitioned data set.
In deep reinforcement learning, building policies of high-quality is challenging when the feature space of states is small and the training data is limited.
Another thread is to transfer knowledge from other source domains such as improving the movie recommendation with the knowledge from the book domain, leading to transfer learning methods.
As artificial intelligence (AI) systems become increasingly ubiquitous, the topic of AI governance for ethical decision-making by AI has captured public imagination.
To meet the standard of differential privacy, noise is usually added into the original data, which inevitably deteriorates the predicting performance of subsequent learning algorithms.
Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or a specific Aspect Term (AT).
We hope this survey can serve as not only an insightful guideline for AutoML beginners but also an inspiration for future research.
To address this problem, transfer learning can be leveraged to accelerate the smart city development, which we term the urban transfer learning paradigm.
We propose a new multi-graph convolutional neural network model to predict the bike flow at station-level, where the key novelty is viewing the bike sharing system from the graph perspective.
In transfer learning, what and how to transfer are two primary issues to be addressed, as different transfer learning algorithms applied between a source and a target domain result in different knowledge transferred and thereby the performance improvement in the target domain.
Based on such training set, L2MT first uses a proposed layerwise graph neural network to learn task embeddings for all the tasks in a multitask problem and then learns an estimation function to estimate the relative test error based on task embeddings and the representation of the multitask model based on a unified formulation.
Existing cross-domain sentiment classification meth- ods cannot automatically capture non-pivots, i. e., the domain- specific sentiment words, and pivots, i. e., the domain-shared sentiment words, simultaneously.
Also, they depend on either common slots or slot entropy, which are not available when the source and target slots are totally disjoint and no database is available to calculate the slot entropy.
CoNet enables dual knowledge transfer across domains by introducing cross connections from one base network to another and vice versa.
By modeling content information as local memories, LCMR attentively learns what to exploit with the guidance of user-item interaction.
RegionTrans aims to effectively transfer knowledge from a data-rich source city to a data-scarce target city.
Training a personalized dialogue system requires a lot of data, and the data collected for a single user is usually insufficient.
Then the built user model is used as a leverage to train the agent model by deep reinforcement learning.
Although existing generative question answering (QA) systems can be applied to knowledge grounded conversation, they either have at most one entity in a response or cannot deal with out-of-vocabulary entities.
We establish the L2T framework in two stages: 1) we first learn a reflection function encrypting transfer learning skills from experiences; and 2) we infer what and how to transfer for a newly arrived pair of domains by optimizing the reflection function.
Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks.
Finally, we use the resulting ensemble of RF and CNN to identify the ridesourcing cars in the candidate pool.
We compare cosine normalization with batch, weight and layer normalization in fully-connected neural networks as well as convolutional networks on the data sets of MNIST, 20NEWS GROUP, CIFAR-10/100 and SVHN.
One way to solve this problem is to consider a collection of multiple users' data as a source domain and an individual user's data as a target domain, and to perform a transfer learning from the source to the target domain.
We now know that mid-level features can greatly enhance the performance of image learning, but how to automatically learn the image features efficiently and in an unsupervised manner is still an open question.