Official Alimama tech channel, showcasing all of Alimama's technical innovations.
The 2023 Tmall Double 11 campaign saw Alibaba’s data‑intelligent tools boost market share to 63.14%, lift GMV by over 6%, and help more than 200 brands achieve double‑digit growth through platforms like ShowMAX, Super Live, and Wanxiang AI, illustrating the power of integrated digital marketing in e‑commerce.
The HC² framework enhances multi‑scenario ad ranking by jointly applying a generalized contrastive loss on shared representations and an individual contrastive loss on scenario‑specific layers, using label‑aware positive sampling, diffusion‑noise negative sampling, and inverse‑similarity weighting, achieving consistent offline gains and up to 2.5% CVR and 3.7% GMV improvements in Alibaba’s live system.
BOMGraph introduces a unified heterogeneous graph neural network that jointly models text, image, and similar‑item search across multiple e‑commerce scenarios, using meta‑path‑guided attention, disentangled scenario‑specific and shared embeddings, and contrastive learning to alleviate sample sparsity, achieving consistent offline and online performance gains.
Taobao Group’s ten large‑model challenges target e‑commerce AI by demanding domain‑specific pre‑training, multi‑step reasoning, extended context handling, factual reliability, intelligent tool orchestration, robust retrieval integration, fuzzy‑intent tool selection, scalable multi‑objective RLHF, improved query rewriting, and knowledge‑driven recommendation.
The paper presents incentive‑compatible, individually rational auction mechanisms for automated ad bidding where advertisers report private budget and ROI constraints, characterizes feasible allocation and payment rules via monotone budget functions, introduces a personalized ranking‑score auction using a “key ROI,” and demonstrates through experiments that the design achieves near‑optimal welfare and revenue while ensuring truthful reporting.
This article explains how the Alibaba‑Mama team addresses constrained ROI bidding in a black‑box adversarial environment by introducing a Minimax Regret Optimization framework that aligns training and test distributions, builds a causal world model, and demonstrates robust performance on synthetic and real‑world ad auctions.
The 23rd CCF C³ Forum, organized by Alibaba’s Alimama and the CCF CTO Club, examined how large‑model AI is reshaping intelligent business technology, from data‑driven to knowledge‑driven approaches, enhancing e‑commerce with smarter search, personalized recommendations, content creation, and guiding merchants on future AI‑native strategies.
The paper, a joint effort by Alibaba Mama and HKBU TMLR, shows that monitoring model dynamics—specifically a newly defined memorization‑discrepancy metric—can reveal hidden accumulative poisoning attacks in online advertising streams, and introduces a discrepancy‑aware correction algorithm that consistently outperforms existing defenses across benchmark datasets.
Megatron-LLaMA is an open‑source high‑performance training framework for LLaMA models, offering tensor, pipeline, and sequence parallelism, an overlapped optimizer, and near‑linear scalability, achieving up to 176% speedup on 32 GPUs and robust performance even with limited network bandwidth.
CC‑GNN addresses three drawbacks of existing graph‑neural retrieval for e‑commerce by adding content phrase nodes, scalable meta‑path message passing, and difficulty‑aware noisy contrastive learning with counterfactual augmentation, achieving up to 16 % recall improvement and notably larger gains on long‑tail queries and cold‑start items.
