Skip to content
Book Open access

Dart: Adaptive Tweedie Objective Mitigates the σ Escape Route in Cross-Platform Popularity Prediction

Sep 2026 · Proceedings of the 20th ACM Conference on Recommender Systems · pp. 145-153 · 0 citations · 13 references

Abstract

Social-media popularity prediction is hampered by a mismatch between its targets—non-negative, zero-inflated, and heavy-tailed—and the Gaussian negative log-likelihood (NLL) and mean squared error (MSE) objectives commonly used to fit them. We examine one consequence, for which we use the descriptive shorthand σ escape route: under heteroscedastic Gaussian NLL an independently predicted scale absorbs large residuals and attenuates the gradient for the mean μ. As a distribution-aware alternative we study an adaptive Tweedie objective—unit deviance with dispersion fixed at ϕ = 1—which couples residual weighting to the mean (Var(Y) = ϕμp) and matches the support of the targets. Architecture-controlled swaps improve Spearman’s ρ for every predictor tested, and Dart, a retrieval-augmented instantiation assembled from established components, attains the highest average ρ across nine platforms in both per-platform (0.395) and leave-one-platform-out (0.275) evaluation, without using any target-platform data. A conventional log (1 + y)-MSE control nevertheless remains competitive under LOPO and is stronger on several top-k metrics, and retrieval helps unevenly across platforms. Objective selection is therefore a first-class design choice, separable from and complementary to retrieval-based context.

Read PDF

Similar papers

#artificial intelligence Preprint Sep 2026

FairDiff: Mitigating the Self-Reinforcing Matthew Effect in Diffusion Recommender Models

FairDiff is proposed, a plug-and-play fairness-aware diffusion framework that achieves state-of-the-art performance while effectively mitigating the self-reinforcing Matthew Effect, highlighting its value as a general framework for DRMs.

Song-Li Wu, Xian-Quan Wang, Zhao-Cheng Du et al. · 2 citations
Book Open access Sep 2026

A Redundancy Reduction Approach for Controllable Sequential Recommendations

This work proposes a decorrelation-regularized training framework that augments next-item prediction with an auxiliary redundancy-reduction term, and instantiate it with BT-SR, which uses the Barlow Twins objective to form label-consistent positive pairs without synthetic corruptions.

Veronika Ivanova, Marina Munkhoeva, Ivan Razvorotnev et al. · 0 citations
#machine learning Preprint Oct 2026

Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models

Masked diffusion language models (dLMs) offer a promising parallel alternative to autoregressive models for complex reasoning. However, they face a distinct credit-assignment challenge, since a few commitments during denoising sharply reduce the uncertainty over the remaining masked positions and shape much of the resp...

S. Kim, Sun-Woo Hong, Younwoo Choi et al. · 0 citations
Preprint Oct 2026

CoTA++: Understanding the Repeat Curse in dMLLMs from an Information Flow Perspective

Diffusion-based multimodal large language models (dMLLMs) decode by iterative denoising with bidirectional attention, which precludes the standard autoregressive key--value cache. Practical deployments therefore rely on approximate caching that reuses intermediate states across denoising steps. Such caching, however, o...

Qi-Yan Zhao, Xiao-Feng Zhang, Xu-Yao Zhang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models

PILL (Probing-based InfiLling with preset-Length-free decoding), an efficient infilling method for DLMs that requires no preset initial length and adds far fewer extra forward passes than baselines, substantially reducing inference time is proposed.

Hao-Bo Xu, Si-Rui Chen, Yuan-Chen Bei et al. · 6 citations
#artificial intelligence Conference Sep 2026

The Limits of Simulated Societies: How Post-Training and Survey Fine-Tuning Erase Cross-Cultural Variance

Using large language models (LLMs) to simulate diverse human populations has the potential to transform many aspects of computational social science, yet many evaluations score the average response rather than the spread of opinion within real groups. Here, we develop a diagnostic framework that measures point accuracy...

Rojin Ziaei · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.