Learning Recommenders for Implicit Feedback with Importance Resampling

Chen, Jin; Lian, Defu; Jin, Binbin; Zheng, Kai; Chen, Enhong

doi:10.1145/3485447.3512075

Cited by 21 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these solutions are only applicable in certain scenarios and cannot produce hard negative samples at scale based on current user interest representations. Finally, the most related hard negative sampling strategies are those that produce negative samples according to the current user representation [5,6,11,33,51]. For example, the work [51] uses a dynamic rejection sampling strategy according to item ranking, the work [11] leverages score-based memory update and variance-based sampling, and a concurrent work [6] generates hard negative samples for sequential recommendation using the Next Negative Item (NNI) Sampler with Pre-selection and Post-selection.…”

Section: Negative Sampling In Recommender Systemsmentioning

confidence: 99%

See 1 more Smart Citation

Rethinking Multi-Interest Learning for Candidate Matching in Recommender Systems

Xie¹,

Gao²,

Zhou³

et al. 2023

Preprint

View full text Add to dashboard Cite

Existing research efforts for multi-interest candidate matching in recommender systems mainly focus on improving model architecture or incorporating additional information, neglecting the importance of training schemes. This work revisits the training framework and uncovers two major problems hindering the expressiveness of learned multi-interest representations. First, the current training objective (i.e., uniformly sampled softmax) fails to effectively train discriminative representations in a multi-interest learning scenario due to the severe increase in easy negative samples. Second, a routing collapse problem is observed where each learned interest may collapse to express information only from a single item, resulting in information loss. To address these issues, we propose the REMI framework, consisting of an Interest-aware Hard Negative mining strategy (IHN) and a Routing Regularization (RR) method. IHN emphasizes interest-aware hard negatives by proposing an ideal sampling distribution and developing a Monte-Carlo strategy for efficient approximation. RR prevents routing collapse by introducing a novel regularization term on the item-to-interest routing matrices. These two components enhance the learned multi-interest representations from both the optimization objective and the composition information. REMI is a general framework that can be readily applied to various existing multi-interest candidate matching methods. Experiments on three real-world datasets show our method can significantly improve state-of-the-art methods with easy implementation and negligible computational overhead. The source code will be released. CCS CONCEPTS• Information systems → Recommender systems.

show abstract

Section: Negative Sampling In Recommender Systemsmentioning

confidence: 99%

“…More details can be found in [2,4]. We adopt the widely used metrics, i.e., Recall, Hit Rate, and NDCG (Normalized Discounted Cumulative Gain) 5 , to evaluate our proposed solution. The metrics are computed with the top 20/50 matched candidates.…”

Section: Training and Evaluationmentioning

confidence: 99%

Rethinking Multi-Interest Learning for Candidate Matching in Recommender Systems

Xie¹,

Gao²,

Zhou³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…We include projects with contribution history of at least 3 months according to their commit history. To ensure that our model generalizes on a wide range of topics, popularity, and project scales, we first select 3 subsets of repositories using their GitHub topics 3 , which are project labels created by the project owners. Then, we randomly sample 300 repositories from each subset considering their numbers of project files and stars.…”

Section: Experiments 41 Experimental Settingsmentioning

confidence: 99%

“…The advances in deep learning have greatly facilitated the evolution of recommender systems [3,16,49,64,65]. In particular, motivated by the success of Graph Neural Networks (GNN) [15,26,70,71], a series of graph-based recommender systems [27,49,52] are proposed, which organize user behaviors into heterogeneous interaction graphs.…”

Section: Recommender Systemsmentioning

confidence: 99%

Code Recommendation for Open Source Software Developers

Jin¹,

Bai²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Open Source Software (OSS) is forming the spines of technology infrastructures, attracting millions of talents to contribute. Notably, it is challenging and critical to consider both the developers' interests and the semantic features of the project code to recommend appropriate development tasks to OSS developers. In this paper, we formulate the novel problem of code recommendation, whose purpose is to predict the future contribution behaviors of developers given their interaction history, the semantic features of source code, and the hierarchical file structures of projects. Considering the complex interactions among multiple parties within the system, we propose CODER, a novel graph-based code recommendation framework for open source software developers. CODER jointly models microscopic user-code interactions and macroscopic userproject interactions via a heterogeneous graph and further bridges the two levels of information through aggregation on file-structure graphs that reflect the project hierarchy. Moreover, due to the lack of reliable benchmarks, we construct three large-scale datasets to facilitate future research in this direction. Extensive experiments show that our CODER framework achieves superior performance under various experimental settings, including intra-project, crossproject, and cold-start recommendation. We will release all the datasets, code, and utilities for data retrieval upon the acceptance of this work.

show abstract

“…However, uniformly sampled negative items may not be informative, contributing little to the gradients and the convergence [28,40]. To overcome this obstacle, researchers have proposed many Hard Negative Sampling (HNS) methods, such as Dynamic Negative Sampling (DNS) [40] and Softmax-based Sampling methods [9,21,33]. Superior to uniform sampling, HNS methods oversample high-scored negative items, which are more informative with large gradients and thus accelerate the convergence [8].…”

Section: Introductionmentioning

confidence: 99%

On the Theories Behind Hard Negative Sampling for Recommendation

Shi,

Chen,

Feng

et al. 2023

Preprint

View full text Add to dashboard Cite

Negative sampling has been heavily used to train recommender models on large-scale data, wherein sampling hard examples usually not only accelerates the convergence but also improves the model accuracy. Nevertheless, the reasons for the effectiveness of Hard Negative Sampling (HNS) have not been revealed yet. In this work, we fill the research gap by conducting thorough theoretical analyses on HNS. Firstly, we prove that employing HNS on the Bayesian Personalized Ranking (BPR) learner is equivalent to optimizing One-way Partial AUC (OPAUC). Concretely, the BPR equipped with Dynamic Negative Sampling (DNS) is an exact estimator, while with softmax-based sampling is a soft estimator. Secondly, we prove that OPAUC has a stronger connection with Top-𝐾 evaluation metrics than AUC and verify it with simulation experiments. These analyses establish the theoretical foundation of HNS in optimizing Top-𝐾 recommendation performance for the first time. On these bases, we offer two insightful guidelines for effective usage of HNS: 1) the sampling hardness should be controllable, e.g., via pre-defined hyper-parameters, to adapt to different Top-𝐾 metrics and datasets; 2) the smaller the 𝐾 we emphasize in Top-𝐾 evaluation metrics, the harder the negative samples we should draw. Extensive experiments on three real-world benchmarks verify the two guidelines. CCS CONCEPTS• Information systems → Recommender systems.

show abstract

Learning Recommenders for Implicit Feedback with Importance Resampling

Cited by 21 publications

References 26 publications

Rethinking Multi-Interest Learning for Candidate Matching in Recommender Systems

Rethinking Multi-Interest Learning for Candidate Matching in Recommender Systems

Code Recommendation for Open Source Software Developers

On the Theories Behind Hard Negative Sampling for Recommendation

Contact Info

Product

Resources

About