Pith. sign in

REVIEW 15 cited by

MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2102.07619 v2 pith:Q57WZY2E submitted 2021-02-09 cs.IR

classification cs.IR
keywords modelsrankingfeaturefeed-forwardmaskblockmasknetbasicbuilding
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Click-Through Rate(CTR) estimation has become one of the most fundamental tasks in many real-world applications and it's important for ranking models to effectively capture complex high-order features. Shallow feed-forward network is widely used in many state-of-the-art DNN models such as FNN, DeepFM and xDeepFM to implicitly capture high-order feature interactions. However, some research has proved that addictive feature interaction, particular feed-forward neural networks, is inefficient in capturing common feature interaction. To resolve this problem, we introduce specific multiplicative operation into DNN ranking system by proposing instance-guided mask which performs element-wise product both on the feature embedding and feed-forward layers guided by input instance. We also turn the feed-forward layer in DNN model into a mixture of addictive and multiplicative feature interactions by proposing MaskBlock in this paper. MaskBlock combines the layer normalization, instance-guided mask, and feed-forward layer and it is a basic building block to be used to design new ranking model under various configurations. The model consisting of MaskBlock is called MaskNet in this paper and two new MaskNet models are proposed to show the effectiveness of MaskBlock as basic building block for composing high performance ranking systems. The experiment results on three real-world datasets demonstrate that our proposed MaskNet models outperform state-of-the-art models such as DeepFM and xDeepFM significantly, which implies MaskBlock is an effective basic building unit for composing new high performance ranking systems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 15 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation

    cs.IR 2026-07 conditional novelty 6.0 of 10

    SpecFormer is a spectral-aware Transformer that flattens the singular-value spectrum of embeddings to prevent embedding/attention collapse, outperforming baselines on CTR benchmarks and scaling with layer depth.

  2. Revisiting Feature Interactions from the Perspective of Quadratic Neural Networks for Click-through Rate Prediction

    cs.IR 2025-05 conditional novelty 6.0 of 10

    Hadamard product feature interactions work because they make CTR models quadratic networks, and the proposed QNN-alpha with multi-head Khatri-Rao product and self-ensemble loss achieves state-of-the-art results on six...

  3. Adaptive Domain Scaling for Personalized Sequential Modeling in Recommenders

    cs.IR 2025-02 conditional novelty 6.0 of 10

    Domain-conditioned generation of per-user sequence item and candidate query representations improves multi-domain target-aware attention in recommenders.

  4. Graph Disentangle Causal Model: Enhancing Causal Inference in Networked Observational Data

    cs.LG 2024-12 conditional novelty 6.0 of 10

    GDC disentangles features into adjustment and confounder representations, aggregates them separately over the network, and uses counterfactual confounders to improve individual treatment effect estimation.

  5. From Collapse to Stability: A Knowledge-Driven Ensemble Framework for Scaling Up Click-Through Rate Prediction Models

    cs.IR 2024-11 conditional novelty 6.0 of 10

    KDEF combines knowledge distillation and deep mutual learning with adaptive exam-score weighting so that CTR ensembles with up to ten sub-networks improve instead of collapse.

  6. Fusion Matters: Learning Fusion in Deep Click-through Rate Prediction Models

    cs.IR 2024-11 conditional novelty 6.0 of 10

    OptFusion automatically learns fusion connections and operations in deep CTR models and reports consistent AUC improvements on Criteo, Avazu, and KDD12.

  7. InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction

    cs.IR 2024-11 conditional novelty 6.0 of 10

    A bidirectional, interleaved interaction module with a separate Cross Arch for selective summarization improves CTR prediction over unidirectional fusion baselines by small margins on public and industrial data.

  8. RAMP: Robust Ad Recommendation Under Limited Personalized-Feature Availability via Masking and Alignment Pathways

    cs.IR 2026-07 conditional novelty 5.0 of 10

    RAMP splits ad prediction into personalized and non-personalized towers, then uses a distillation-style loss to transfer knowledge so non-personalized predictions stay accurate when user features are absent.

  9. Synergizing Implicit and Explicit User Interests: A Multi-Embedding Retrieval Framework at Pinterest

    cs.IR 2025-06 conditional novelty 5.0 of 10

    A production recommender framework combines a differentiable clustering module for implicit interests and conditional retrieval for explicit followed topics, deployed at Pinterest home feed.

  10. Breaker: Removing Shortcut Cues with User Clustering for Single-slot Recommendation System

    cs.IR 2025-06 conditional novelty 5.0 of 10

    Breaker improves single-slot recommendation by clustering users into groups, which makes the model work harder on user-side features and focus more on user-item preferences.

  11. The Evolution of Embedding Table Optimization and Multi-Epoch Training in Pinterest Ads Conversion

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A frequency-adaptive learning rate that slows updates to rare embedding IDs reduces multi-epoch overfitting for some sparse ad-conversion objectives, but not the sparsest, and its advantage disappears after days of co...

  12. Towards Unifying Feature Interaction Models for Click-Through Rate Prediction

    cs.IR 2024-11 conditional novelty 5.0 of 10

    Most explicit feature-interaction CTR models can be expressed as combinations of an interaction function, a layer pooling strategy, and a layer aggregator; the derived PFL model is competitive with state-of-the-art methods.

  13. Decoupled Entity Representation Learning for Pinterest Ads Ranking

    cs.IR 2025-09 conditional novelty 4.0 of 10

    Pre-computed user and Pin embeddings from multi-tower models improve Pinterest ad ranking by small but statistically significant margins.

  14. Hadamard product in deep learning: Introduction, Advances and Challenges

    cs.LG 2025-04 conditional novelty 4.0 of 10

    A survey that taxonomizes deep learning applications of the Hadamard product into four domains and argues it is a core architectural primitive.

  15. Improving feature interactions at Pinterest under industry constraints

    cs.IR 2024-12 conditional novelty 4.0 of 10

    A Pinterest team found that parallel MaskNet blocks plus stacked DCNv2 layers improved Homefeed engagement by 1.42% in saves while respecting memory, latency, and reproducibility constraints.

Pith tools