Modelling Contextual Information in Session-Aware Recommender Systems with Neural Networks

By Bartlomiej Twardowski. 2016

116 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. Yan Wang
2. Quan Z. Sheng
3. Longbing Cao
4. Shoujin Wang
5. Yi Tay
6. Dietmar Jannach
7. Ed H. Chi
8. Malte Ludewig

In Information Systems

1. Dietmar Jannach
2. Malte Ludewig
3. Yan Wang
4. Longbing Cao
5. Quan Z. Sheng
6. Shoujin Wang
7. Yi Tay
8. Ed H. Chi

In Management Science and Operations Research

1. Malte Ludewig
2. Dietmar Jannach
3. Yan Wang
4. Longbing Cao
5. Quan Z. Sheng
6. Shoujin Wang
7. Yi Tay
8. Aixin Sun

Citations in the corpus

• Contextual Sequence Modeling for Recommendation with Recurrent Neural Networks (2017, methodology): “Neural architecture proposed in [20] produced an embedding of sequence of events using RNN to predict the next item represented as a set of attributes.”
• When Recurrent Neural Networks meet the Neighborhood for Session-Based Recommendation (2017, unknown): “In [15] and [32] RNN-based approaches were recently proposed that leverage additional item features to achieve higher accuracy.”
• Evaluation of session-based recommendation algorithms (2018, methodology): “Generally, it is of course surprising that a recent and popular RNN-based method is not substantially better than longer-existing nearest neighbor approaches.”
• STAMP: Short-Term Attention/Memory Priority Model for Session-based Recommendation (2018, background): “Although RNN models have been proven useful in capturing users’ general interests from a sequence of actions[20], learning to predict from sessions is still a challenging problem to tackle largely due to the uncertainty inherent in user behavior and the limited information provided by browser sessio”
• Deep Learning Based Recommender System (2017, background): “[40, 41, 49, 104, 105] [26, 65, 118] [4, 49, 61, 126, 135] [32, 64, 120, 138] [10, 91] [3, 102] (Diversity) [22] (Coverage)”
• Sequence-Aware Recommender Systems (2018, unknown): “ EC 20M 6M 143M N/A [43] Epinions EC 40k 110k 181k N/A [43] RecSys Chall. 2015 EC N/A 38k 34M 9.5M [45] Ta-feng EC 32k 24k 829k N/A [110,116] TMall EC 1k 10k 5k N/A [110,116] AVITO EC N/A 4k 767k 32k [107] Retailrocket EC 1.4M 235k 2.7M N/A [2] Microsoft WWW 27k/13k 8k 13k/55k 32k/5k [125,126] MSNBC”
• Latent Cross: Making Use of Context in Recurrent Recommender Systems (2018, methodology): “We compare the RNNLatentCross model described above to highly tuned models of alternative forms: • RRN: Use [ v j ; w ∆ t ] as the input to the RNN; similar to [43] and [41].”
• A Survey on Session-based Recommender Systems (2019, background): “Session-aware recommendations with neural network [105] L, O, MT, A, SL RNN Item DeepPage [146] O, MT, NA, SL RL, RNN Item”