KATRec: Knowledge Aware aTtentive Sequential Recommendations

Amjadi, Mehrnaz; Taheri, Seyed Danial Mohseni; Tulabandhula, Theja

doi:10.1007/978-3-030-88942-5_24

“…We implement these architectures using TensorFlow version 2 [1]. 2 Note that for our experiments we reuse only the architectures of these models and not the training methods or hyper-parameters. Indeed, because our goal is to research the impact of the training task, the appropriate training parameters may differ from the original implementation.…”

Section: Methodsmentioning

confidence: 99%

“…1 We do not report results for BERT4Rec models for the Gowalla dataset because due to large number of items in this dataset, we were not able to train the model. 2 We report results for BERT4rec-16h separately due to its larger training time. 2, we note that general magnitudes of the reported effectiveness results are smaller than those reported in [42] indeed, as stated in Section 5.4, in contrast to [42], we follow recent advice [5,20] to avoid sampled metrics, instead preferring the more accurate unsampled metrics.…”

Section: Data Splitting and Evaluation Measuresmentioning

confidence: 99%

See 1 more Smart Citation

Effective and Efficient Training for Sequential Recommendation using Recency Sampling

Petrov

¹

,

Macdonald

²

2022

Proceedings of the 16th ACM Conference on Recommender Systems

View full text Add to dashboard Cite

Many modern sequential recommender systems use deep neural networks, which can effectively estimate the relevance of items but require a lot of time to train. Slow training increases expenses, hinders product development timescales and prevents the model from being regularly updated to adapt to changing user preferences. Training such sequential models involves appropriately sampling past user interactions to create a realistic training objective. The existing training objectives have limitations. For instance, next item prediction never uses the beginning of the sequence as a learning target, thereby potentially discarding valuable data. On the other hand, the item masking used by BERT4Rec is only weakly related to the goal of the sequential recommendation; therefore, it requires much more time to obtain an effective model. Hence, we propose a novel Recency-based Sampling of Sequences training objective that addresses both limitations. We apply our method to various recent and state-of-the-art model architectures -such as GRU4Rec, Caser, and SASRec. We show that the models enhanced with our method can achieve performances exceeding or very close to stateof-the-art BERT4Rec, but with much less training time.

show abstract

“…1 We do not report results for BERT4Rec models for the Gowalla dataset because due to large number of items in this dataset, we were not able to train the model. 2 We report results for BERT4rec-16h separately due to its larger training time.…”

Section: Resultsmentioning

confidence: 99%

“…Yelp 1 -is a businesses reviews dataset. It is another popular dataset for sequential recommendations [2,3,30,37,46,54]. As for MovieLens-20M, we consider all user reviews as positives.…”

Section: Datasetsmentioning

confidence: 99%

Effective and Efficient Training for Sequential Recommendation using Recency Sampling

Petrov¹,

Macdonald²

2022

Preprint

1

0

View full text Add to dashboard Cite

Many modern sequential recommender systems use deep neural networks, which can effectively estimate the relevance of items but require a lot of time to train. Slow training increases expenses, hinders product development timescales and prevents the model from being regularly updated to adapt to changing user preferences. Training such sequential models involves appropriately sampling past user interactions to create a realistic training objective. The existing training objectives have limitations. For instance, next item prediction never uses the beginning of the sequence as a learning target, thereby potentially discarding valuable data. On the other hand, the item masking used by BERT4Rec is only weakly related to the goal of the sequential recommendation; therefore, it requires much more time to obtain an effective model. Hence, we propose a novel Recency-based Sampling of Sequences training objective that addresses both limitations. We apply our method to various recent and state-of-the-art model architectures -such as GRU4Rec, Caser, and SASRec. We show that the models enhanced with our method can achieve performances exceeding or very close to stateof-the-art BERT4Rec, but with much less training time.

show abstract