1. |
|
|
2. |
|
|
3. |
- Boman, Magnus, et al.
(author)
-
Trust in Micro Service Environments
- 2006. - 1
-
Reports (other academic/artistic)abstract
- Report produced in the project Enabling and Promoting Trust in Micro Service Environments (EPTMSE) with a web site at www.trust-eze.org. The report gives an overview of the concept of trust in domains such as psychology, sociology, philosophy, and computer science, and then describes the current domain of Micro Service Environments - open and unregulated electronic service environments - where users can create, use, and share electronic services, and where the need for decentralized trust mechanisms is high. Some design and implementation choices and solutions for trust mechanisms are suggested.
|
|
4. |
|
|
5. |
- Cöster, Rickard, 1973-
(author)
-
Algorithms and Representations for Personalised Information Access
- 2005
-
Doctoral thesis (other academic/artistic)abstract
- Personalised information access systems use historical feedback data, such as implicit and explicit ratings for textual documents and other items, to better locate the right or relevant information for individual users.Three topics in personalised information access are addressed: learning from relevance feedback and document categorisation by the use of concept-based text representations, the need for scalable and accurate algorithms for collaborative filtering, and the integration of textual and collaborative information access.Two concept-based representations are investigated that both map a sparse high-dimensional term space to a dense concept space. For learning from relevance feedback, it is found that the representation combined with the proposed learning algorithm can improve the results of novel queries, when queries are more elaborate than a few terms. For document categorisation, the representation is found useful as a complement to a traditional word-based one.For collaborative filtering, two algorithms are proposed: the first for the case where there are a large number of users and items, and the second for use in a mobile device. It is demonstrated that memory-based collaborative filtering can be more efficiently implemented using inverted files, with equal or better accuracy, and that there is little reason to use the traditional in-memory vector approach when the data is sparse. An empirical evaluation of the algorithm for collaborative filtering on mobile devices show that it can generate accurate predictions at a high speed using a small amount of resources.For integration, a system architecture is proposed where various combinations of content-based and collaborative filtering can be implemented. The architecture is general in the sense that it provides an abstract representation of documents and user profiles, and provides a mechanism for incorporating new retrieval and filtering algorithms at any time.In conclusion this thesis demonstrates that information access systems can be personalised using scalable and accurate algorithms and representations for the increased benefit of the user.
|
|
6. |
|
|
7. |
- Cöster, Rickard, et al.
(author)
-
Incremental Collaborative Filtering for Mobile Devices
- 2005. - 1
-
Conference paper (peer-reviewed)abstract
- This paper describes how collaborative filtering can be used for mobile devices. When the user is connected to a central repository, the algorithm selects a subset of profiles to store on the device. When the user is not connected to the repository, the predictions can be incrementally updated to reflect new or updated ratings. Experiments on a movie data set show that the method can dramatically reduce the data needed while still performing nearly as good as a centralized approach.
|
|
8. |
- Cöster, Rickard, et al.
(author)
-
Inverted file search algorithms for collaborative filtering
- 2002. - 1
-
Conference paper (peer-reviewed)abstract
- This paper explores the possibility of using a disk based inverted file structure for collaborative filtering. Our hypothesis is that this allows for faster calculation of predictions and also that early termination heuristics may be used to further speed up the filtering process and perhaps even improve the quality of the predictions. In an experiment on the EachMovie dataset this was tested. Our results indicate that searching the inverted file structure is many times faster than general in-memory vector search, even for very large profiles. The Continue termination heuristics produces the best ranked predictions in our experiments, and Quit is the top performer in terms of speed.
|
|
9. |
- Cöster, Rickard, et al.
(author)
-
Selective compound splitting of Swedish queries for boolean combination of truncated terms
- 2003. - 1
-
Conference paper (peer-reviewed)abstract
- In compounding languages such as Swedish, it is often neccessary to split compound words when indexing documents or queries. One of the problems is that it is difficult to find constituents that express a concept similar to that expressed by the compound. The approach taken here is to expand a query with the leading constituents of the compound words. Every query term is truncated so as to increase recall by hopefully finding other compounds with the leading constituent as prefix. This approach increase recall in a rather uncontrolled way, so we use a Boolean quorum-level type of search to rank documents both according to a tf-idf factor but also to the number of matching Boolean combinations. The Boolean combinations performed relatively well, taken into consideration that the queries were very short (maximum five search terms). Also included in this paper are the results of two other methods we are currently working on in our lab; one for re-ranking search results on the basis of stylistic analysis of documents, and one for dimensionality reduction using Random Indexing.
|
|
10. |
- Isaksson, Martin, et al.
(author)
-
Adaptive Expert Models for Personalization in Federated Learning
- 2022
-
In: International Workshop on Trustworthy Federated Learningin Conjunction with IJCAI 2022 (FL-IJCAI'22).
-
Conference paper (peer-reviewed)abstract
- Federated Learning (FL) is a promising framework for distributed learning whendata is private and sensitive. However, the state-of-the-art solutions in thisframework are not optimal when data is heterogeneous and non-Independent andIdentically Distributed (non-IID). We propose a practical and robust approachto personalization in FL that adjusts to heterogeneous and non-IID data bybalancing exploration and exploitation of several global models. To achieve ouraim of personalization, we use a Mixture of Experts (MoE) that learns to groupclients that are similar to each other, while using the global models moreefficiently. We show that our approach achieves an accuracy up to 29.78 % andup to 4.38 % better compared to a local model in a pathological non-IIDsetting, even though we tune our approach in the IID setting.
|
|