arXiv subjects

Xianzheng Song

Publications and source records attributed to Xianzheng Song.

4 recordsLinked to original sources

arXiv2026

DHSched: Stateless Control for Stateful Real-Time Avatar Serving

Real-time avatar services run long-lived, GPU-backed sessions that transform a continuous text stream into speech, facial motion, rendered video, and RTC media. Elastic operation repeatedly reassigns these sessions across Workers. A reassignment updates shared placement state while the previous GPU runtime and RTC connection remain alive, opening a gap between control-plane assignment and execution authority. A stateful controller serializes ownership by retaining per-session authority, placing that state on the controller's scaling and failover path. We present DHSched, a control plane that manages long-lived stateful sessions through stateless peer Dispatch replicas. DHSched externalizes session ownership as a generation identified by (WorkerID, epoch). Dispatch conditionally commits each generation. Infer-Controller claims and revalidates the same generation before releasing state-advancing input. A stale runtime loses execution authority even if it remains alive. DHSched ranks candidates from periodically refreshed load views while keeping capacity admission authoritative. Recovery advances the same generation path via source-epoch guards and source-independent reconstruction. DHSched runs in our production avatar-serving stack, which reached 49,987 concurrent live sessions. On 10 June 2026, it completed 9,927 session migrations with no observed dual-owner conflicts or capacity overshoots. At the production peak, CreateLive latency was 98.3 ms at P99 and PushText latency was 16.5 ms at P99. Across 100,000 randomized ownership runs, assignment-time, claim-only, and WorkerID-only protocols permit stale execution, while DHSched records no dual-owner or stale-generation release.

cs.DC↗

arXiv2023

InferTurbo: A Scalable System for Boosting Full-graph Inference of Graph Neural Network over Huge Graphs

GNN inference is a non-trivial task, especially in industrial scenarios with giant graphs, given three main challenges, i.e., scalability tailored for full-graph inference on huge graphs, inconsistency caused by stochastic acceleration strategies (e.g., sampling), and the serious redundant computation issue. To address the above challenges, we propose a scalable system named InferTurbo to boost the GNN inference tasks in industrial scenarios. Inspired by the philosophy of ``think-like-a-vertex", a GAS-like (Gather-Apply-Scatter) schema is proposed to describe the computation paradigm and data flow of GNN inference. The computation of GNNs is expressed in an iteration manner, in which a vertex would gather messages via in-edges and update its state information by forwarding an associated layer of GNNs with those messages and then send the updated information to other vertexes via out-edges. Following the schema, the proposed InferTurbo can be built with alternative backends (e.g., batch processing system or graph computing system). Moreover, InferTurbo introduces several strategies like shadow-nodes and partial-gather to handle nodes with large degrees for better load balancing. With InferTurbo, GNN inference can be hierarchically conducted over the full graph without sampling and redundant computation. Experimental results demonstrate that our system is robust and efficient for inference tasks over graphs containing some hub nodes with many adjacent edges. Meanwhile, the system gains a remarkable performance compared with the traditional inference pipeline, and it can finish a GNN inference task over a graph with tens of billions of nodes and hundreds of billions of edges within 2 hours.

cs.LG↗

arXiv2020

AGL: a Scalable System for Industrial-purpose Graph Machine Learning

Machine learning over graphs have been emerging as powerful learning tools for graph data. However, it is challenging for industrial communities to leverage the techniques, such as graph neural networks (GNNs), and solve real-world problems at scale because of inherent data dependency in the graphs. As such, we cannot simply train a GNN with classic learning systems, for instance parameter server that assumes data parallel. Existing systems store the graph data in-memory for fast accesses either in a single machine or graph stores from remote. The major drawbacks are in three-fold. First, they cannot scale because of the limitations on the volume of the memory, or the bandwidth between graph stores and workers. Second, they require extra development of graph stores without well exploiting mature infrastructures such as MapReduce that guarantee good system properties. Third, they focus on training but ignore the optimization of inference over graphs, thus makes them an unintegrated system. In this paper, we design AGL, a scalable, fault-tolerance and integrated system, with fully-functional training and inference for GNNs. Our system design follows the message passing scheme underlying the computations of GNNs. We design to generate the $k$-hop neighborhood, an information-complete subgraph for each node, as well as do the inference simply by merging values from in-edge neighbors and propagating values to out-edge neighbors via MapReduce. In addition, the $k$-hop neighborhood contains information-complete subgraphs for each node, thus we simply do the training on parameter servers due to data independency. Our system AGL, implemented on mature infrastructures, can finish the training of a 2-layer graph attention network on a graph with billions of nodes and hundred billions of edges in 14 hours, and complete the inference in 1.2 hour.

cs.SI↗

arXiv2020

DSSLP: A Distributed Framework for Semi-supervised Link Prediction

Link prediction is widely used in a variety of industrial applications, such as merchant recommendation, fraudulent transaction detection, and so on. However, it's a great challenge to train and deploy a link prediction model on industrial-scale graphs with billions of nodes and edges. In this work, we present a scalable and distributed framework for semi-supervised link prediction problem (named DSSLP), which is able to handle industrial-scale graphs. Instead of training model on the whole graph, DSSLP is proposed to train on the \emph{$k$-hops neighborhood} of nodes in a mini-batch setting, which helps reduce the scale of the input graph and distribute the training procedure. In order to generate negative examples effectively, DSSLP contains a distributed batched runtime sampling module. It implements uniform and dynamic sampling approaches, and is able to adaptively construct positive and negative examples to guide the training process. Moreover, DSSLP proposes a model-split strategy to accelerate the speed of inference process of the link prediction task. Experimental results demonstrate that the effectiveness and efficiency of DSSLP in serval public datasets as well as real-world datasets of industrial-scale graphs.

cs.SI↗