REVIEW 10 cited by
On the Embedding Collapse when Scaling up Recommendation Models
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
Signed reviews
read the original abstract
Recent advances in foundation models have led to a promising trend of developing large recommendation models to leverage vast amounts of available data. Still, mainstream models remain embarrassingly small in size and na\"ive enlarging does not lead to sufficient performance gain, suggesting a deficiency in the model scalability. In this paper, we identify the embedding collapse phenomenon as the inhibition of scalability, wherein the embedding matrix tends to occupy a low-dimensional subspace. Through empirical and theoretical analysis, we demonstrate a \emph{two-sided effect} of feature interaction specific to recommendation models. On the one hand, interacting with collapsed embeddings restricts embedding learning and exacerbates the collapse issue. On the other hand, interaction is crucial in mitigating the fitting of spurious features as a scalability guarantee. Based on our analysis, we propose a simple yet effective multi-embedding design incorporating embedding-set-specific interaction modules to learn embedding sets with large diversity and thus reduce collapse. Extensive experiments demonstrate that this proposed design provides consistent scalability and effective collapse mitigation for various recommendation models. Code is available at this repository: https://github.com/thuml/Multi-Embedding.
Forward citations
Cited by 10 Pith papers
-
ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale Recommendation
ROCS restructures recommendation models so user-side computation is shared across all candidate items, yielding up to 3x serving throughput at equal or better prediction quality.
-
Scaling Transformers for Discriminative Recommendation via Generative Pretraining
Generative pretraining plus sparse-embedding freezing makes large Transformer ranking models scale consistently, following a power law from 13K to 0.3B dense parameters.
-
SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation
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.
-
FuXi-\beta: Towards a Lightweight and Fast Large-Scale Generative Recommendation Model
FuXi-β shows that removing query-key attention and using a functional relative time bias makes generative recommendation Transformers faster and, on industrial datasets, more accurate.
-
MTGR: Industrial-Scale Generative Recommendation Framework in Meituan
MTGR augments an HSTU-style generative ranking model with DLRM cross features and user-level aggregation, and reports a successful industrial deployment at Meituan with offline and online gains.
-
Large Foundation Model for Ads Recommendation
Tencent's LFM4Ads transfers user, item, and user-item cross representations from a pre-trained foundation model into downstream ad models via feature, module, and model-level mechanisms, reporting a 2.45% platform-wid...
-
The Evolution of Embedding Table Optimization and Multi-Epoch Training in Pinterest Ads Conversion
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...
-
FuXi-$\alpha$: Scaling Recommendation Model with Feature Interaction Enhanced Transformer
FuXi-alpha, a sequential recommender with decoupled temporal, positional, and semantic attention channels plus a two-stage FFN, reports gains over HSTU and positive online engagement results.
-
Towards Unifying Feature Interaction Models for Click-Through Rate Prediction
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.
-
Scaling New Frontiers: Insights into Large Recommendation Models
Deep HSTU models tend to improve recall, ranking, multi-behavior, and multi-domain performance on public data, while GPT and SASRec fail to scale, though the evidence lacks error bars.
Discussion (0). Continue with ORCID to comment.