Matches in SemOpenAlex for { <https://semopenalex.org/work/W3111101221> ?p ?o ?g. }
- W3111101221 abstract "Nowadays, gathering high-quality training data from multiple data sources with privacy preservation is a crucial challenge to training high-performance machine learning models. The potential solutions could break the barriers among isolated data corpus, and consequently enlarge the range of data available for processing. To this end, both academic researchers and industrial vendors are recently strongly motivated to propose two main-stream folders of solutions mainly based on software constructions: 1) Secure Multi-party Learning (MPL for short); and 2) Federated Learning (FL for short). The above two technical folders have their advantages and limitations when we evaluate them according to the following five criteria: security, efficiency, data distribution, the accuracy of trained models, and application scenarios. Motivated to demonstrate the research progress and discuss the insights on the future directions, we thoroughly investigate these protocols and frameworks of both MPL and FL. At first, we define the problem of Training machine learning Models over Multiple data sources with Privacy Preservation (TMMPP for short). Then, we compare the recent studies of TMMPP from the aspects of the technical routes, the number of parties supported, data partitioning, threat model, and machine learning models supported, to show their advantages and limitations. Next, we investigate and evaluate five popular FL platforms. Finally, we discuss the potential directions to resolve the problem of TMMPP in the future." @default.
- W3111101221 created "2020-12-21" @default.
- W3111101221 creator A5011724449 @default.
- W3111101221 creator A5017059967 @default.
- W3111101221 creator A5024591862 @default.
- W3111101221 creator A5077588879 @default.
- W3111101221 date "2020-12-06" @default.
- W3111101221 modified "2023-09-27" @default.
- W3111101221 title "SoK: Training Machine Learning Models over Multiple Sources with Privacy Preservation" @default.
- W3111101221 cites W121345474 @default.
- W3111101221 cites W1480225633 @default.
- W3111101221 cites W1485800369 @default.
- W3111101221 cites W1493343761 @default.
- W3111101221 cites W1497332869 @default.
- W3111101221 cites W1497981337 @default.
- W3111101221 cites W150223756 @default.
- W3111101221 cites W1520270249 @default.
- W3111101221 cites W1540408657 @default.
- W3111101221 cites W1575598731 @default.
- W3111101221 cites W1635361314 @default.
- W3111101221 cites W173953576 @default.
- W3111101221 cites W1798609567 @default.
- W3111101221 cites W1826277484 @default.
- W3111101221 cites W1873763122 @default.
- W3111101221 cites W1969009977 @default.
- W3111101221 cites W1971991172 @default.
- W3111101221 cites W1984680759 @default.
- W3111101221 cites W1985511977 @default.
- W3111101221 cites W1996068512 @default.
- W3111101221 cites W1996360405 @default.
- W3111101221 cites W2001084165 @default.
- W3111101221 cites W2019891719 @default.
- W3111101221 cites W2027595342 @default.
- W3111101221 cites W2031533839 @default.
- W3111101221 cites W2039605106 @default.
- W3111101221 cites W2082624086 @default.
- W3111101221 cites W2088492763 @default.
- W3111101221 cites W2108834246 @default.
- W3111101221 cites W2109426455 @default.
- W3111101221 cites W2112380340 @default.
- W3111101221 cites W2132172731 @default.
- W3111101221 cites W2134167315 @default.
- W3111101221 cites W2136114025 @default.
- W3111101221 cites W2141420453 @default.
- W3111101221 cites W2153689444 @default.
- W3111101221 cites W2156030242 @default.
- W3111101221 cites W2159024459 @default.
- W3111101221 cites W2160502124 @default.
- W3111101221 cites W2283463896 @default.
- W3111101221 cites W2300242332 @default.
- W3111101221 cites W2380240963 @default.
- W3111101221 cites W2402235285 @default.
- W3111101221 cites W2435473771 @default.
- W3111101221 cites W2473418344 @default.
- W3111101221 cites W2530417694 @default.
- W3111101221 cites W2535838896 @default.
- W3111101221 cites W2541884796 @default.
- W3111101221 cites W2544267735 @default.
- W3111101221 cites W2581082771 @default.
- W3111101221 cites W2606882085 @default.
- W3111101221 cites W2620512600 @default.
- W3111101221 cites W2679684481 @default.
- W3111101221 cites W2744999500 @default.
- W3111101221 cites W2765200655 @default.
- W3111101221 cites W2767079719 @default.
- W3111101221 cites W2768347741 @default.
- W3111101221 cites W2777914285 @default.
- W3111101221 cites W2781091734 @default.
- W3111101221 cites W2794541489 @default.
- W3111101221 cites W2860079600 @default.
- W3111101221 cites W2895865029 @default.
- W3111101221 cites W2900319533 @default.
- W3111101221 cites W2902114605 @default.
- W3111101221 cites W2912213068 @default.
- W3111101221 cites W2914508875 @default.
- W3111101221 cites W2914853145 @default.
- W3111101221 cites W2929650703 @default.
- W3111101221 cites W2941310685 @default.
- W3111101221 cites W2949377959 @default.
- W3111101221 cites W2950527268 @default.
- W3111101221 cites W2951832089 @default.
- W3111101221 cites W2962804345 @default.
- W3111101221 cites W2963106566 @default.
- W3111101221 cites W2963300197 @default.
- W3111101221 cites W2963401954 @default.
- W3111101221 cites W2963456518 @default.
- W3111101221 cites W2963540401 @default.
- W3111101221 cites W2963733194 @default.
- W3111101221 cites W2963752132 @default.
- W3111101221 cites W2963849169 @default.
- W3111101221 cites W2970408908 @default.
- W3111101221 cites W2972652285 @default.
- W3111101221 cites W2973629179 @default.
- W3111101221 cites W2976335444 @default.
- W3111101221 cites W2979681796 @default.
- W3111101221 cites W2984644945 @default.
- W3111101221 cites W2990885002 @default.
- W3111101221 cites W2992272656 @default.
- W3111101221 cites W2995022099 @default.
- W3111101221 cites W2996786840 @default.