The importance of hyperparameters selection within small datasets

Ashrafi, Parivash; Sun, Yi; Davey, Neil; Adams, Rod; Brown, Marc; Prapopoulou, Maria; Moss, Gary P.

doi:10.1109/ijcnn.2015.7280645

Cited by 3 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where p = 10 in our experiment. s 2 Meta is trained by standard SGD with learning rate 0.0001 and weight decay 1e-5, implemented with PyTorch 5 1.0 in Python 3.6 and runs on a single Linux server with 8 NVIDIA GeForce GTX 1080.…”

Section: A Appendixmentioning

confidence: 99%

“…Although the cold-start problem can be tackled by cross-domain recommender systems with domain knowledge being transferred, they still require a large amount of shared samples across domains [21,32,43]. Secondly, when training a predictive model on a new scenario, the hyperparameters often have a great influence on the performance and optimal hyperparameters in different scenarios may differ significantly [5,50]. Finding a right combination of hyperparameters usually requires great human efforts along with sufficient observations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sequential Scenario-Specific Meta Learner for Online Recommendation

Wang

Yang

et al. 2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Cold-start problems are long-standing challenges for practical recommendations. Most existing recommendation algorithms rely on extensive observed data and are brittle to recommendation scenarios with few interactions. This paper addresses such problems using few-shot learning and meta learning. Our approach is based on the insight that having a good generalization from a few examples relies on both a generic model initialization and an effective strategy for adapting this model to newly arising tasks. To accomplish this, we combine the scenario-specific learning with a model-agnostic sequential meta-learning and unify them into an integrated end-toend framework, namely Scenario-specific Sequential Meta learner (or s 2 Meta ). By doing so, our meta-learner produces a generic initial model through aggregating contextual information from a variety of prediction tasks while effectively adapting to specific tasks by leveraging learning-to-learn knowledge. Extensive experiments on various real-world datasets demonstrate that our proposed model can achieve significant gains over the state-of-the-arts for cold-start problems in online recommendation 1 . Deployment is at the Guess You Like session, the front page of the Mobile Taobao; and the illustration video can also be watched from the link 2 .

show abstract

Section: A Appendixmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%