Pith. sign in

REVIEW 6 cited by

Zero-Shot Recommender Systems

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 2105.08318 v2 pith:HPKPZXQX submitted 2021-05-18 cs.LG cs.AIcs.IR

classification cs.LGcs.AIcs.IR
keywords itemsuserszero-shotzesrecdatasetoverlappingamountchicken-and-egg
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Performance of recommender systems (RS) relies heavily on the amount of training data available. This poses a chicken-and-egg problem for early-stage products, whose amount of data, in turn, relies on the performance of their RS. On the other hand, zero-shot learning promises some degree of generalization from an old dataset to an entirely new dataset. In this paper, we explore the possibility of zero-shot learning in RS. We develop an algorithm, dubbed ZEro-Shot Recommenders (ZESRec), that is trained on an old dataset and generalize to a new one where there are neither overlapping users nor overlapping items, a setting that contrasts typical cross-domain RS that has either overlapping users or items. Different from categorical item indices, i.e., item ID, in previous methods, ZESRec uses items' natural-language descriptions (or description embeddings) as their continuous indices, and therefore naturally generalize to any unseen items. In terms of users, ZESRec builds upon recent advances on sequential RS to represent users using their interactions with items, thereby generalizing to unseen users as well. We study three pairs of real-world RS datasets and demonstrate that ZESRec can successfully enable recommendations in such a zero-shot setting, opening up new opportunities for resolving the chicken-and-egg problem for data-scarce startups or early-stage products.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

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

  1. ATLAS: Learning to Recommend Across Unseen Domains

    cs.IR 2026-08 conditional novelty 6.0 of 10

    A frozen recommender trained on five Amazon domains beats most zero-shot baselines on ten unseen domains, with an average HitRate gain of about 24%.

  2. Probabilistic Residual Learning for Online Recommendations

    cs.IR 2026-07 conditional novelty 6.0 of 10

    PRL adds a cluster-aware, causality-adjusted residual correction layer to any base recommender, improving cold-start cross-domain recommendation accuracy in experiments.

  3. Federated User Behavior Modeling for Privacy-Preserving LLM Recommendation

    cs.IR 2026-04 unverdicted novelty 6.0 of 10

    SF-UBM enables privacy-preserving cross-domain LLM recommendation by federating semantic item representations, distilling domain knowledge, and aligning preferences into LLM soft prompts.

  4. Towards Comprehensible Recommendation with Large Language Model Fine-tuning

    cs.IR 2025-08 conditional novelty 6.0 of 10

    CURec aligns an LLM with recommendation objectives via RL, generates personalized user patterns and item-reason texts, and corrects them through a chronological loop, improving top-K recall and NDCG on MovieLens and Amazon.

  5. Your Spending Needs Attention: Modeling Financial Habits with Transformers

    cs.IR 2025-07 conditional novelty 6.0 of 10

    A causal transformer pre-trained with next-token prediction on tokenized bank transactions, fused end-to-end with tabular features, lifts recommendation test AUC by 1.25% relative over a LightGBM baseline at Nubank.

  6. Rethinking Semantic Collaborative Integration: Why Alignment Is Not Enough

    cs.IR 2026-04 unverdicted novelty 5.0 of 10

    Semantic and collaborative representations show low item-level overlap on sparse data, so global alignment suppresses complementary signals and a shared-plus-private fusion design is needed instead.

Pith tools