Learning and adaptivity in interactive recommender systems

By Tariq Mahmood, Francesco Ricci. 2007

122 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiangnan He
2. Tat-seng Chua
3. Xing Xie
4. Xiang Wang
5. Fuli Feng
6. Fuzheng Zhang
7. Dawei Yin
8. Wenqiang Lei

In Information Systems

1. Xiangnan He
2. Tat-seng Chua
3. Xing Xie
4. Xiang Wang
5. Fuli Feng
6. Fuzheng Zhang
7. M. M. Afsar
8. Trafford Crump

In Management Science and Operations Research

1. Xiangnan He
2. M. M. Afsar
3. Trafford Crump
4. Behrouz Homayoun Far
5. Tat-seng Chua
6. Fuli Feng
7. Xiangyu Zhao
8. Jiliang Tang

Citations in the corpus

• DRN: A Deep Reinforcement Learning Framework for News Recommendation (2018, methodology): “…different from the MAB group of methods [5, 7, 23, 40, 44, 50] due to its explicit modeling of future rewards, and different from previous MDP methods [27, 35, 36, 38] using user log due to its continuous representation of state and action, and the capability to scale to large systems.”
• Reinforcement Learning based Recommender Systems: A Survey (2021, methodology): “use +1 in terminal state and a negative number otherwise [86], + 5 for adding a product to travel plan, +1 for showing result page, 0 otherwise [88], and +100 for buying a book, -30 for user quit, and 0 otherwise [92].”
• Recommender Systems (2016, unknown): “in [389, 390] model the sequential learning problem as a Markov Decision Process (MDP), and use reinforcement learning techniques to measure the impact of various choices.”
• Evaluating Recommendation Systems (2011, methodology): “Another type of adaptivity is the rate by which the system adapts to a user’s personal preferences [37], or to changes in user profile [34].”
• A Survey on Conversational Recommender Systems (2020, unknown): “and in particular in knowledge-based approaches, dialogue management is based on a finite state machine, which not only defines the possible states but also the allowed transitions between the states [82, 83, 145, 147]. In the Advisor Suite framework [55, 58], for example, the entire recommendation ”
• Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning (2018, background): “s [23, 24]. Typically, a recommendation procedure can be modeled as interactions between users and recommender agent (RA). It consistsoftwophases:1)usermodelconstructionand2)recommendation generation [14]. During the interaction, the recommender agent builds a user model to learn users’ preferences ”
• TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation (2023, methodology): “Moving forward, we plan to explore more efficient methods to activate the recommendation ability of larger models and tune LLMs to handle multiple recommendation tasks simultaneously.”
• Advances and Challenges in Conversational Recommender Systems: A Survey (2021, methodology): “For example, Mahmood and Ricci [111] introduce a modelbased techniques and use the policy iteration algorithm [162] to acquire an adaptive strategy.”