arXiv subjects

Changping Wang

Publications and source records attributed to Changping Wang.

At least 19 recordsLinked to original sources

arXiv2026

UniVA: Unified Value Alignment for Generative Recommendation in Online Advertising at Tencent

Generative Recommendation (GR) reformulates recommendation as next-token generation over item Semantic IDs (SIDs) and has shown promise in industrial applications. However, extending GR to advertising is non-trivial, as advertising recommendation must jointly account for user relevance and commercial value. This creates a mismatch: high generation likelihood does not necessarily imply high advertising utility. As a result, valuable ads may be poorly distinguished in the SID space, pruned during autoregressive decoding, or missed when request-invalid branches consume limited beam capacity during online serving. To address this problem, we propose UniVA, a Unified Value Alignment framework for generative advertising recommendation. UniVA aligns commercial value across the entire pipeline of SID construction, autoregressive decoding, and online serving. Commercial SID Tokenization injects business attributes and bid information into SID construction. A Generation-as-Ranking SID Decoder then fuses generation scores with token-level value estimates during autoregressive decoding. {Finally, Value-Aware Constrained Serving restricts the fused decoding process to request-valid SID paths through a personalized trie.} Experiments on the Tencent WeChat Channels advertising platform show that UniVA achieves a 37.04\% relative improvement in offline Hit Rate@100 over the baseline and lifts gross merchandise value (GMV) by 1.5\% in online A/B tests.

cs.IR↗

arXiv2026

Breaking the Curse of Repulsion: Remoteness-Aware Control of Negative Off-Policy Updates

Off-policy policy optimization reuses historical behavior, including negative-advantage samples that suppress known failures. We show that repeated reuse can turn this useful signal into excessive repulsion: as the learner moves away from a historical negative action, subsequent updates make that action increasingly remote without necessarily reducing its update strength. Our aggregate theory characterizes the resulting transition from a stable displacement beyond the positive-only target to persistent drift and the loss of finite stable equilibria; controlled strength sweeps show that an intermediate displacement can improve held-out reward. The relevant learner-relative coordinate is squared standardized distance for Gaussian policies and surprisal for categorical policies. We introduce Dynamic Remoteness-Aware Policy Optimization (DRPO), which leaves the negative update unchanged in the near field and exponentially attenuates its remote tail. DRPO restores eventual inward Gaussian drift for every fixed finite negative-to-positive mass ratio, yields an explicit ultimate-bound radius, and changes categorical support suppression from exponential to polynomial probability decay. External diagnostics and controlled interventions isolate remoteness-dependent policy geometry as a source of negative-update amplification and show that selective tapering can remove its far-field effect without discarding useful local feedback.

cs.LG↗

arXiv2026

S-GRec: Personalized Semantic-Aware Generative Recommendation with Asymmetric Advantage

Generative recommendation models sequence generation to produce items end-to-end, but training from behavioral logs often provides weak supervision on underlying user intent. Although Large Language Models (LLMs) offer rich semantic priors that could supply such supervision, direct adoption in industrial recommendation is hindered by two obstacles: semantic signals can conflict with platform business objectives, and LLM inference is prohibitively expensive at scale. This paper presents S-GRec, a semantic-aware framework that decouples an online lightweight generator from an offline LLM-based semantic judge for train-time supervision. S-GRec introduces a two-stage Personalized Semantic Judge (PSJ) that produces interpretable aspect evidence and learns user-conditional aggregation from pairwise feedback, yielding stable semantic rewards. To prevent semantic supervision from deviating from business goals, Asymmetric Advantage Policy Optimization (A2PO) anchors optimization on business rewards (e.g., eCPM) and injects semantic advantages only when they are consistent. Extensive experiments on public benchmarks and a large-scale production system validate both effectiveness and scalability, including statistically significant gains in CTR and a 1.19\% lift in GMV in online A/B tests, without requiring real-time LLM inference.

cs.IR↗

arXiv2026

Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation

Generative recommendation via autoregressive models has unified retrieval and ranking into a single conditional generation framework. However, fine-tuning these models with Reinforcement Learning (RL) often suffers from a fundamental probability-reward mismatch. Conventional likelihood-dominated decoding (e.g., beam search) exhibits a myopic bias toward locally probable prefixes, which causes two critical failures: (1) insufficient exploration, where high-reward items in low-probability branches are prematurely pruned and rarely sampled, and (2) advantage compression, where trajectories sharing high-probability prefixes receive highly correlated rewards with low within-group variance, yielding a weak comparative signal for RL. To address these challenges, we propose V-STAR, a Value-guided Sampling and Tree-structured Advantage Reinforcement framework. V-STAR forms a self-evolving loop via two synergistic components. First, a Value-Guided Efficient Decoding (VED) is developed to identify decisive nodes and selectively deepen high-potential prefixes. This improves exploration efficiency without exhaustive tree search. Second, we propose Sibling-GRPO, which exploits the induced tree topology to compute sibling-relative advantages and concentrates learning signals on decisive branching decisions. Extensive experiments on both offline and online datasets demonstrate that V-STAR outperforms state-of-the-art baselines, delivering superior accuracy and candidate-set diversity under strict latency constraints.

cs.AI↗

arXiv2026

Two classes of Willmore Surfaces in $\mathbb{S}^2\times \mathbb{S}^2$

We establish two classification theorems for Willmore surfaces in $\mathbb{S}^2 \times \mathbb{S}^2$. Firstly, we prove that a Willmore surface which is also minimal must be either a special complex curve given by a slice or a diagonal; or, a minimal surface in a totally geodesic submanifold $\mathbb{S}^2 \times \mathbb{S}^1$ described by a solution of the sinh-Gordon equation in one variable. Secondly, we demonstrate that a Willmore surface is of product type if and only if it is the product of an elastic curve in $\mathbb{S}^2$ and a great circle.

math.DG↗

arXiv2025

GPR: Towards a Generative Pre-trained One-Model Paradigm for Large-Scale Advertising Recommendation

As an intelligent infrastructure connecting users with commercial content, advertising recommendation systems play a central role in information flow and value creation within the digital economy. However, existing multi-stage advertising recommendation systems suffer from objective misalignment and error propagation, making it difficult to achieve global optimality, while unified generative recommendation models still struggle to meet the demands of practical industrial applications. To address these issues, we propose GPR (Generative Pre-trained Recommender), the first one-model framework that redefines advertising recommendation as an end-to-end generative task, replacing the traditional cascading paradigm with a unified generative approach. To realize GPR, we introduce three key innovations spanning unified representation, network architecture, and training strategy. First, we design a unified input schema and tokenization method tailored to advertising scenarios, mapping both ads and organic content into a shared multi-level semantic ID space, thereby enhancing semantic alignment and modeling consistency across heterogeneous data. Second, we develop the Heterogeneous Hierarchical Decoder (HHD), a dual-decoder architecture that decouples user intent modeling from ad generation, achieving a balance between training efficiency and inference flexibility while maintaining strong modeling capacity. Finally, we propose a multi-stage joint training strategy that integrates Multi-Token Prediction (MTP), Value-Aware Fine-Tuning and the Hierarchy Enhanced Policy Optimization (HEPO) algorithm, forming a complete generative recommendation pipeline that unifies interest modeling, value alignment, and policy optimization. GPR has been fully deployed in the Tencent Weixin Channels advertising system, delivering significant improvements in key business metrics including GMV and CTCVR.

cs.IR↗

arXiv2024

Morse index of minimal products of minimal submanifolds in spheres

Tang-Zhang, Choe-Hoppe, showed independently that one can produce minimal submanifolds in spheres via Clifford type minimal product of minimal submanifolds. In this note, we show that the minimal product is immersed by its first eigenfunctions (of its Laplacian) if and only if the two beginning minimal submanifolds are immersed by their first eigenfunctions. Moreover, we give estimates of Morse index and nullity of the minimal product. In particular, we show that the Clifford minimal submanifold $\left(\sqrt{\frac{n_1}{n}}S^{n_1},\cdots,\sqrt{\frac{n_k}{n}}S^{n_k}\right)\subset S^{n+k-1}$ has index $(k-1)(n+k+1)$ and nullity $(k-1)\sum_{1\leq i<j\leq k}(n_i+1)(n_j+1)$ (with $n=\sum n_j$).

math.DG↗

arXiv2023

Willmore surfaces in 4-dimensional conformal manifolds

This paper is dedicated to the exploration of the conformal Willmore functional for surfaces within 4-dimensional conformal manifolds. We provide a detailed calculation of both the first and second variations, and present the Euler-Lagrange equation of this functional in a conformally invariant form. Utilizing the second variation formula we derived, we demonstrate that the Clifford torus in $\mathbb{C}P^2$ is strictly Willmore-stable. This finding strongly supports the conjecture proposed by Montiel and Urbano [J. reine angew. Math. 546 2002, 139-154], which posits that the Clifford torus in $\mathbb{C}P^2$ minimizes the Willmore functional among all tori. Moreover, by applying our formula to complex curves in $\mathbb{C}P^2$, we establish that the first nonzero eigenvalue of the Jacobi operator is at least 12. In the context of 4-dimensional locally symmetric spaces, we construct several holomorphic differentials to show that among all minimal 2-spheres, only those super-minimal ones can be Willmore.

math.DG↗

arXiv2023

Instant Representation Learning for Recommendation over Large Dynamic Graphs

Recommender systems are able to learn user preferences based on user and item representations via their historical behaviors. To improve representation learning, recent recommendation models start leveraging information from various behavior types exhibited by users. In real-world scenarios, the user behavioral graph is not only multiplex but also dynamic, i.e., the graph evolves rapidly over time, with various types of nodes and edges added or deleted, which causes the Neighborhood Disturbance. Nevertheless, most existing methods neglect such streaming dynamics and thus need to be retrained once the graph has significantly evolved, making them unsuitable in the online learning environment. Furthermore, the Neighborhood Disturbance existing in dynamic graphs deteriorates the performance of neighbor-aggregation based graph models. To this end, we propose SUPA, a novel graph neural network for dynamic multiplex heterogeneous graphs. Compared to neighbor-aggregation architecture, SUPA develops a sample-update-propagate architecture to alleviate neighborhood disturbance. Specifically, for each new edge, SUPA samples an influenced subgraph, updates the representations of the two interactive nodes, and propagates the interaction information to the sampled subgraph. Furthermore, to train SUPA incrementally online, we propose InsLearn, an efficient workflow for single-pass training of large dynamic graphs. Extensive experimental results on six real-world datasets show that SUPA has a good generalization ability and is superior to sixteen state-of-the-art baseline methods. The source code is available at https://github.com/shatter15/SUPA.

cs.IR↗

arXiv2023

Multi-behavior Self-supervised Learning for Recommendation

Modern recommender systems often deal with a variety of user interactions, e.g., click, forward, purchase, etc., which requires the underlying recommender engines to fully understand and leverage multi-behavior data from users. Despite recent efforts towards making use of heterogeneous data, multi-behavior recommendation still faces great challenges. Firstly, sparse target signals and noisy auxiliary interactions remain an issue. Secondly, existing methods utilizing self-supervised learning (SSL) to tackle the data sparsity neglect the serious optimization imbalance between the SSL task and the target task. Hence, we propose a Multi-Behavior Self-Supervised Learning (MBSSL) framework together with an adaptive optimization method. Specifically, we devise a behavior-aware graph neural network incorporating the self-attention mechanism to capture behavior multiplicity and dependencies. To increase the robustness to data sparsity under the target behavior and noisy interactions from auxiliary behaviors, we propose a novel self-supervised learning paradigm to conduct node self-discrimination at both inter-behavior and intra-behavior levels. In addition, we develop a customized optimization strategy through hybrid manipulation on gradients to adaptively balance the self-supervised learning task and the main supervised recommendation task. Extensive experiments on five real-world datasets demonstrate the consistent improvements obtained by MBSSL over ten state-of-the art (SOTA) baselines. We release our model implementation at: https://github.com/Scofield666/MBSSL.git.

cs.IR↗

arXiv2022

M\"{o}bius Homogeneous Hypersurfaces in $\mathbb{S}^{n+1}$

Let $\mathbb{M}(\mathbb{S}^{n+1})$ denote the M\"{o}bius transformation group of the $(n+1)$-dimensional sphere $\mathbb{S}^{n+1}$. A hypersurface $x:M^n\to \mathbb{S}^{n+1}$ is called a M\"{o}bius homogeneous hypersurface if there exists a subgroup $G$ of $\mathbb{M}(\mathbb{S}^{n+1})$ such that the orbit $G\cdot p=x(M^n), p\in x(M^n)$. In this paper, the M\"{o}bius homogeneous hypersurfaces are classified completely up to a M\"{o}bius transformation of $\mathbb{S}^{n+1}$.

math.DG↗

arXiv2022

HybridGNN: Learning Hybrid Representation in Multiplex Heterogeneous Networks

Recently, graph neural networks have shown the superiority of modeling the complex topological structures in heterogeneous network-based recommender systems. Due to the diverse interactions among nodes and abundant semantics emerging from diverse types of nodes and edges, there is a bursting research interest in learning expressive node representations in multiplex heterogeneous networks. One of the most important tasks in recommender systems is to predict the potential connection between two nodes under a specific edge type (i.e., relationship). Although existing studies utilize explicit metapaths to aggregate neighbors, practically they only consider intra-relationship metapaths and thus fail to leverage the potential uplift by inter-relationship information. Moreover, it is not always straightforward to exploit inter-relationship metapaths comprehensively under diverse relationships, especially with the increasing number of node and edge types. In addition, contributions of different relationships between two nodes are difficult to measure. To address the challenges, we propose HybridGNN, an end-to-end GNN model with hybrid aggregation flows and hierarchical attentions to fully utilize the heterogeneity in the multiplex scenarios. Specifically, HybridGNN applies a randomized inter-relationship exploration module to exploit the multiplexity property among different relationships. Then, our model leverages hybrid aggregation flows under intra-relationship metapaths and randomized exploration to learn the rich semantics. To explore the importance of different aggregation flow and take advantage of the multiplexity property, we bring forward a novel hierarchical attention module which leverages both metapath-level attention and relationship-level attention. Extensive experimental results suggest that HybridGNN achieves the best performance compared to several state-of-the-art baselines.

cs.LG↗

arXiv2021

Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation

Recently, micro-video sharing platforms such as Kuaishou and Tiktok have become a major source of information for people's lives. Thanks to the large traffic volume, short video lifespan and streaming fashion of these services, it has become more and more pressing to improve the existing recommender systems to accommodate these challenges in a cost-effective way. In this paper, we propose a novel concept-aware denoising graph neural network (named CONDE) for micro-video recommendation. CONDE consists of a three-phase graph convolution process to derive user and micro-video representations: warm-up propagation, graph denoising and preference refinement. A heterogeneous tripartite graph is constructed by connecting user nodes with video nodes, and video nodes with associated concept nodes, extracted from captions and comments of the videos. To address the noisy information in the graph, we introduce a user-oriented graph denoising phase to extract a subgraph which can better reflect the user's preference. Despite the main focus of micro-video recommendation in this paper, we also show that our method can be generalized to other types of tasks. Therefore, we also conduct empirical studies on a well-known public E-commerce dataset. The experimental results suggest that the proposed CONDE achieves significantly better recommendation performance than the existing state-of-the-art solutions.

cs.IR↗

arXiv2021

Expanding Semantic Knowledge for Zero-shot Graph Embedding

Zero-shot graph embedding is a major challenge for supervised graph learning. Although a recent method RECT has shown promising performance, its working mechanisms are not clear and still needs lots of training data. In this paper, we give deep insights into RECT, and address its fundamental limits. We show that its core part is a GNN prototypical model in which a class prototype is described by its mean feature vector. As such, RECT maps nodes from the raw-input feature space into an intermediate-level semantic space that connects the raw-input features to both seen and unseen classes. This mechanism makes RECT work well on both seen and unseen classes, which however also reduces the discrimination. To realize its full potentials, we propose two label expansion strategies. Specifically, besides expanding the labeled node set of seen classes, we can also expand that of unseen classes. Experiments on real-world datasets validate the superiority of our methods.

cs.LG↗

arXiv2020

Willmore deformations between minimal surfaces in $H^{n+2}$ and $S^{n+2}$

In this paper we show that locally there exists a Willmore deformation between minimal surfaces in $S^{n+2}$ and minimal surfaces in $H^{n+2}$, i.e., there exists a smooth family of Willmore surfaces $\{y_t,t\in[0,1]\}$ such that $(y_t)|_{t=0}$ is conformally equivalent to a minimal surface in $S^{n+2}$ and $(y_t)|_{t=1}$ is conformally equivalent to a minimal surface in $H^{n+2}$. For some cases the deformations are global. Consider the Willmore deformations of the Veronese two-sphere and its generalizations in $S^4$, for any positive number $W_0\in\mathbb R^+$, we construct complete minimal surfaces in $H^4$ with Willmore energy being equal to $W_0$. An example of complete minimal Möbius strip in $H^4$ with Willmore energy $\frac{6\sqrt{5}π}{5}\approx10.733π$ is also presented. We also show that all isotropic minimal surfaces in $S^4$ admit Jacobi fields different from Killing fields, i.e., they are not "isolated".

math.DG↗

arXiv2020

On embedded minimal hypersurfaces in $S^{n+1}$ with symmetries

In this note, we generalize a characterization of the Clifford torus due to Ros. Let $f:M\rightarrow S^{n+1}$ be an embedded closed minimal hypersurface. Assume there are $(n+2)$ great hyperspheres of $S^{n+1}$ perpendicular to each other, such that $M$ is symmetric with respect to them. Let $S$ denote the square of the length of the second fundamental form of $f$ and let $\bar S=\frac{1}{Vol(M)}\int_{M} Sd M$ be the average of $S$. Then $\bar S\geq n$ with equality holding if and only if $f$ is the Clifford torus $C_{m,n-m}$. It can be rewritten as a Simons' type theorem: If $0\leq \int_M (n-S)d M$, then either $S\equiv0$ or $S\equiv n$. This answers partially a conjecture by Perdomo. Moreover, the estimate of the Willmore energy of $f$ is built: $W(M)\geq n^{\frac{n}{2}}Vol(M)$.

math.DG↗

arXiv2017

A Möbius scalar curvature rigidity on compact conformally flat hypersurfaces in $\mathbb{S}^{n+1}$

In this paper, we study conformally flat hypersurfaces of dimension $n(\geq 4)$ in $\mathbb{S}^{n+1}$ using the framework of Möbius geometry. First, we classify and explicitly express the conformally flat hypersurfaces of dimension $n(\geq 4)$ with constant Möbius scalar curvature under the Möbius transformation group of $\mathbb{S}^{n+1}$. Second, we prove that if the conformally flat hypersurface with constant Möbius scalar curvature $R$ is compact, then $$R=(n-1)(n-2)r^2, ~~0<r<1,$$ and the compact conformally flat hypersurface is Möbius equivalent to the torus $$\mathbb{ S}^1(\sqrt{1-r^2})\times \mathbb{S}^{n-1}(r)\hookrightarrow \mathbb{S}^{n+1}.$$

math.DG↗

arXiv2016

Scalar Invariants of surfaces in conformal 3-sphere via Minkowski spacetime

For a surface in 3-sphere, by identifying the conformal round 3-sphere as the projectivized positive light cone in Minkowski 5-spacetime, we use the conformal Gauss map and the conformal transform to construct the associate homogeneous 4-surface in Minkowski 5-spacetime. We then derive the local fundamental theorem for a surface in conformal round 3-sphere from that of the associate 4-surface in Minkowski 5-spacetime. More importantly, following the idea of Fefferman and Graham, we construct local scalar invariants for a surface in conformal round 3-sphere. One distinct feature of our construction is to link the classic work of Blaschke to the works of Bryan and Fefferman-Graham.

math.DG↗