JDJiandong Ding

Jiandong Ding

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jiandong Ding has a total of 35 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Mitigating Popularity Bias in Recommendation with Global Listwise Learning and Progressive Bi-Weighting

    by Tianyu Zhu, Jiandong Ding, Yansong Shi, Guoqing Chen, Jian-Yun Nie

    In recommender systems, user feedback typically follows a long-tail distribution, which leads many recommendation algorithms to exacerbate popularity bias by disproportionately favoring popular items. To mitigate this issue, recent studies have employed Inverse Propensity Scoring (IPS) to rebalance training data via reweighting user–item interactions. However, the effectiveness of IPS-based approaches is often constrained by locally unbiased objectives and inaccurate propensity estimation. In this article, we propose Multinomial Likelihood with Bi-Weighting (Mult-BiW) to address these limitations. First, we introduce a debiasing framework, termed Mult-IPS, which integrates multinomial likelihood with IPS to capture global and unbiased user preferences over the entire item set. Second, we develop a Bi-Weighting (BiW) strategy that jointly leverages propensity scores and a collection model, incorporating a smoothing mechanism to enhance the robustness of propensity estimation. We further provide theoretical analyses that establish an upper bound on the empirical bias and characterize the optimal form of the collection model. Third, to mitigate the adverse effects of aggressive reweighting on representation learning, we design a Progressive Bi-Weighting strategy that gradually transitions from discriminative representation learning to popularity debiasing. Extensive experiments on real-world datasets show that Mult-BiW consistently outperforms state-of-the-art baselines.

  • Open Access

    Personalized Task Dependency Graphs for Mitigating Signal Erosion in Multi-Task Recommendation

    by Fuyuan Liu, Tiandeng Wu, Yaqun Fang, Wei Zhou, Zehao Zhou, Wenping Chen, Qishun Mei, Jiaxin Zhou, Heng Chang, Yi Cao, et al.

    Optimizing multiple conversion objectives is a core challenge in industrial recommendation, often limited by signal erosion in rigid architectures. Existing Multi-Task Learning (MTL) methods typically enforce uniform dependency strengths across a static conversion funnel, overlooking how task correlations naturally vary based on item characteristics. Hierarchical message passing along these fixed chains leads to cumulative signal attenuation, which degrades performance on sparse, deep-funnel objectives. To address this, we propose the Personalized Task Dependency Graphs (PTDG). While respecting necessary physical causal constraints (e.g., Click → Pay), PTDG dynamically ''rewires'' the intensity of dependency pathways for each item via low-rank approximation to ensure structural robustness. We implement a GCN-based propagation with hard causal masking to establish adaptive information shortcuts. Additionally, we introduce an Adaptive Progressive Masking (APM) strategy that decouples shared parameters according to task sparsity, helping to stabilize optimization. Experiments on KuaiRand1K and an industrial dataset show that PTDG significantly improves AUC on sparse conversion tasks by up to 1.45%, while maintaining comparable performance on dense objectives. Online A/B testing shows PTDG improves Conversion Rate (CVR) by 1.2% and effective Cost Per Mille (eCPM) by 1.9% relative to the baseline.

  • Open Access

    SIDInspector: A Mapping-First Diagnostic Resource for Semantic-ID Tokenizers

    by Jiandong Ding, Heng Chang, Huijie Qin, Tianying Liu

    Semantic-ID (SID) tokenizers define the item address space consumed by generative recommenders. Yet their exported mappings remain difficult to inspect consistently before downstream training. We introduce SIDInspector, a mapping-first diagnostic resource that exposes coverage gaps, full-code aliasing, behaviorally weak prefixes, tail compression, and prefix fan-out. Its adapter contract normalizes item mappings, metadata, interactions, and optional generator traces; validation checks the resulting artifact; and mapping-level probes characterize utilization, aliasing, neighborhood alignment, popularity allocation, and structural cost. Optional interfaces extend the resource to temporal churn and generator traces. We evaluate SIDInspector on four tokenizer lines with explicit provenance. A same-item Musical study compares controlled GRID-style RQ-KMeans exports at two capacity settings with a bounded ReSID/GAOQ export; released LETTER and LC-Rec mappings test the contract on official item-index artifacts. The larger-budget GRID-style row has D2 full-code aliasing of 0.779, versus 0.977 for the width-64 row, while ReSID/GAOQ reaches 0.000. The D3 ordering differs: a deterministic category-prefix control reaches 0.447 versus 0.055–0.154 for the learned exports. Together, these results distinguish capacity, addressability, and behavioral alignment at the artifact level. Across additional datasets, D3 varies under the same category-prefix control. A bounded fixed-reranker probe links D3 to candidate exposure; ranking quality is assessed downstream.

  • Open Access

    Zero-Observation User Reactivation with Gap-Driven Dimensional Gating

    by Jiandong Ding, Tianying Liu, Fuyuan Liu, Huijie Qin, Tiandeng Wu

  • Open Access

    Beyond the Flat Sequence: Hierarchical and Preference-Aware Generative Recommendations

    by Zerui Chen, Heng Chang, Tianying Liu, Chuantian Zhou, Yi Cao, Jiandong Ding, Ming Liu, Bing Qin

    Generative Recommenders (GRs), exemplified by the Hierarchical Sequential Transduction Unit (HSTU), have emerged as a powerful paradigm for modeling long user interaction sequences. However, we observe that their ''flat-sequence'' assumption overlooks the rich, intrinsic structure of user behavior. This leads to two key limitations: a failure to capture the temporal hierarchy of session-based engagement, and computational inefficiency, as dense attention introduces significant noise that obscures true preference signals within semantically sparse histories, which deteriorates the quality of the learned representations. To this end, we propose a novel framework named HPGR (Hierarchical and Preference-aware Generative Recommender), built upon a two-stage paradigm that injects these crucial structural priors into the model to handle the drawback. Specifically, HPGR comprises two synergistic stages. First, a structure-aware pre-training stage employs a session-based Masked Item Modeling (MIM) objective to learn a hierarchically-informed and semantically rich item representation space. Second, a preference-aware fine-tuning stage leverages these powerful representations to implement a Preference-Guided Sparse Attention mechanism, which dynamically constrains computation to only the most relevant historical items, enhancing both efficiency and signal-to-noise ratio. Empirical experiments on a large-scale proprietary industrial dataset from APPGallery and an online A/B test verify that HPGR achieves state-of-the-art performance over multiple strong baselines, including HSTU and MTGR.


  • Open Access

    RPE4Rec: Enhancing Dynamic Node Retrieval with Efficient Relative Position Encoding for Recommendation Systems

    by Ke Cheng, Heng Chang, Pengyang Wang, Liang Gu, Jiandong Ding, Yi Cao, Junchen Ye, Bowen Du


  • Open Access

    Unified Low-rank Compression Framework for Click-through Rate Prediction

    by Hao Yu, Minghao Fu, Jiandong Ding, Yusheng Zhou, Jianxin Wu

    Deep Click-Through Rate (CTR) prediction models play an important role in modern industrial recommendation scenarios. However, high memory overhead and computational costs limit their deployment in resource-constrained environments. Low-rank approximation is an effective method for computer vision and natural language processing models, but its application in compressing CTR prediction models has been less explored. Due to the limited memory and computing resources, compression of CTR prediction models often confronts three fundamental challenges, i.e., (1). How to reduce the model sizes to adapt to edge devices? (2). How to speed up CTR prediction model inference? (3). How to retain the capabilities of original models after compression? Previous low-rank compression research mostly uses tensor decomposition, which can achieve a high parameter compression ratio, but brings in AUC degradation and additional computing overhead. To address these challenges, we propose a unified low-rank decomposition framework for compressing CTR prediction models. We find that even with the most classic matrix decomposition SVD method, our framework can achieve better performance than the original model. To further improve the effectiveness of our framework, we locally compress the output features instead of compressing the model weights. Our unified low-rank compression framework can be applied to embedding tables and MLP layers in various CTR prediction models. Extensive experiments on two academic datasets and one real industrial benchmark demonstrate that, with 3--5× model size reduction, our compressed models can achieve both faster inference and higher AUC than the uncompressed original models. Our code is at https://github.com/yuhao318/Atomic_Feature_Mimicking.