Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMechanism Design for Multi-Party Machine Learning
88
0
0.0
(
0
)
Added by
Mengjing Chen
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
In a multi-party machine learning system, different parties cooperate on optimizing towards better models by sharing data in a privacy-preserving way. A major challenge in learning is the incentive issue. For example, if there is competition among the parties, one may strategically hide his data to prevent other parties from getting better models. In this paper, we study the problem through the lens of mechanism design and incorporate the features of multi-party learning in our setting. First, each agents valuation has externalities that depend on others types and actions. Second, each agent can only misreport a type lower than his true type, but not the other way round. We call this setting interdependent value with type-dependent action spaces. We provide the optimal truthful mechanism in the quasi-monotone utility setting. We also provide necessary and sufficient conditions for truthful mechanisms in the most general case. Finally, we show the existence of such mechanisms is highly affected by the market growth rate and provide empirical analysis.
rate research
Read More
We study the problem of allocating impressions to sellers in e-commerce websites, such as Amazon, eBay or Taobao, aiming to maximize the total revenue generated by the platform. We employ a general framework of reinforcement mechanism design, which uses deep reinforcement learning to design efficient algorithms, taking the strategic behaviour of the sellers into account. Specifically, we model the impression allocation problem as a Markov decision process, where the states encode the history of impressions, prices, transactions and generated revenue and the actions are the possible impression allocations in each round. To tackle the problem of continuity and high-dimensionality of states and actions, we adopt the ideas of the DDPG algorithm to design an actor-critic policy gradient algorithm which takes advantage of the problem domain in order to achieve convergence and stability. We evaluate our proposed algorithm, coined IA(GRU), by comparing it against DDPG, as well as several natural heuristics, under different rationality models for the sellers - we assume that sellers follow well-known no-regret type strategies which may vary in their degree of sophistication. We find that IA(GRU) outperforms all algorithms in terms of the total revenue.
A distributed machine learning platform needs to recruit many heterogeneous worker nodes to finish computation simultaneously. As a result, the overall performance may be degraded due to straggling workers. By introducing redundancy into computation, coded machine learning can effectively improve the runtime performance by recovering the final computation result through the first $k$ (out of the total $n$) workers who finish computation. While existing studies focus on designing efficient coding schemes, the issue of designing proper incentives to encourage worker participation is still under-explored. This paper studies the platforms optimal incentive mechanism for motivating proper workers participation in coded machine learning, despite the incomplete information about heterogeneous workers computation performances and costs. A key contribution of this work is to summarize workers multi-dimensional heterogeneity as a one-dimensional metric, which guides the platforms efficient selection of workers under incomplete information with a linear computation complexity. Moreover, we prove that the optimal recovery threshold $k$ is linearly proportional to the participator number $n$ if we use the widely adopted MDS (Maximum Distance Separable) codes for data encoding. We also show that the platforms increased cost due to incomplete information disappears when worker number is sufficiently large, but it does not monotonically decrease in worker number.
Secure multi-party computation (MPC) allows parties to perform computations on data while keeping that data private. This capability has great potential for machine-learning applications: it facilitates training of machine-learning models on private data sets owned by different parties, evaluation of one partys private model using another partys private data, etc. Although a range of studies implement machine-learning models via secure MPC, such implementations are not yet mainstream. Adoption of secure MPC is hampered by the absence of flexible software frameworks that speak the language of machine-learning researchers and engineers. To foster adoption of secure MPC in machine learning, we present CrypTen: a software framework that exposes popular secure MPC primitives via abstractions that are common in modern machine-learning frameworks, such as tensor computations, automatic differentiation, and modular neural networks. This paper describes the design of CrypTen and measure its performance on state-of-the-art models for text classification, speech recognition, and image classification. Our benchmarks show that CrypTens GPU support and high-performance communication between (an arbitrary number of) parties allows it to perform efficient private evaluation of modern machine-learning models under a semi-honest threat model. For example, two parties using CrypTen can securely predict phonemes in speech recordings using Wav2Letter faster than real-time. We hope that CrypTen will spur adoption of secure MPC in the machine-learning community.
Agent technology, a new paradigm in software engineering, has received attention from research and industry since 1990s. However, it is still not used widely to date because it requires expertise on both programming and agent technology; gaps among requirements, agent design, and agent deployment also pose more difficulties. Goal Net methodology attempts to solve these issues with a goal-oriented approach that resembles human behaviours, and an agent designer that supports agent development using this philosophy. However, there are limitations on existing Goal Net Designer, the design and modelling component of the agent designer. Those limitations, including limited access, difficult deployment, inflexibility in user operations, design workflows against typical Goal Net methodology workflows, and lack of data protection, have inhibited widespread adoption of Goal Net methodology. Motivated by this, this book focuses on improvements on Goal Net Designer. In this project, Goal Net Designer is completely re-implemented using new technology with optimised software architecture and design. It allows access from all major desktop operating systems, as well as in web environment via all modern browsers. Enhancements such as refined workflows, model validation tool, access control, team collaboration tool, and link to compiler make Goal Net Designer a fully functional and powerful Integrated Development Environment. User friendliness and usability are greatly enhanced by simplifying users actions to accomplish their tasks. User behaviour logging and quantitative feedback channel are also included to allow Goal Net Designer to continuously evolve with the power of big data analytics in future. To evaluate the new Goal Net Designer, a teachable agent has been developed with the help of Goal Net Designer and the development process is illustrated in a case study.
The performance of machine learning algorithms heavily relies on the availability of a large amount of training data. However, in reality, data usually reside in distributed parties such as different institutions and may not be directly gathered and integrated due to various data policy constraints. As a result, some parties may suffer from insufficient data available for training machine learning models. In this paper, we propose a multi-party dual learning (MPDL) framework to alleviate the problem of limited data with poor quality in an isolated party. Since the knowledge sharing processes for multiple parties always emerge in dual forms, we show that dual learning is naturally suitable to handle the challenge of missing data, and explicitly exploits the probabilistic correlation and structural relationship between dual tasks to regularize the training process. We introduce a feature-oriented differential privacy with mathematical proof, in order to avoid possible privacy leakage of raw features in the dual inference process. The approach requires minimal modifications to the existing multi-party learning structure, and each party can build flexible and powerful models separately, whose accuracy is no less than non-distributed self-learning approaches. The MPDL framework achieves significant improvement compared with state-of-the-art multi-party learning methods, as we demonstrated through simulations on real-world datasets.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
