GIFT: Graph-guIded Feature Transfer for Cold-Start Video Click-Through Rate Prediction

Abstract

Short video has witnessed rapid growth in China and shows a promising market for promoting the sales of products in e-commerce platforms like Taobao. To ensure the freshness of the content, the platform needs to release a large number of new videos every day, which makes the conventional click-through rate (CTR) prediction model suffer from the severe item cold-start problem.In this paper, we propose GIFT, an efficient Graph-guIded Feature Transfer system, to fully take advantages of the rich information of warmed-up videos that related to the cold-start video. More specifically, we conduct feature transfer from warmed-up videos to those cold-start ones by involving the physical and semantic linkages into a heterogeneous graph. The former linkages consist of those explicit relationships (e.g., sharing the same category, under the same authorship etc.), while the latter measure the proximity of multimodal representations of two videos. In practice, the style, content, and even the recommendation pattern are pretty similar among those physically or semantically related videos. Besides, in order to provide the robust id representations and historical statistics obtained from warmed-up neighbors that cold-start videos covet most, we elaborately design the transfer function to make aware of different transferred features from different types of nodes and edges along the metapath on the graph. Extensive experiments on a large real-world dataset show that our GIFT system outperforms SOTA methods significantly and brings a 6.82% lift on click-through rate (CTR) in the homepage of Taobao App.

Sequence-Based Target Coin Prediction for Cryptocurrency Pump-and-Dump

“…), and market movement signals 1 hour prior to the pump time. Different ranges of time windows (𝑥 = [1,3,6,12,24,48,60,72]) are used to calculate statistics such as price, returns vary from lengths of time. For sequence features, we aggregate historically pumped coins based on channel id and sort them according to pump time to construct the sequence.…”

“…Under such a setting, we observe that the coin-side cold-start problem occurs in an end-to-end training manner. Similar to the item-side cold start problem in recommendation field [12], the coinside cold-start problem occurs in two situations: 1. coins pumped in the testing set are never be pumped in the training set; 2. coins in the testing set are never exist in the training set. Coins falling into one of these cases can make the model hard to classify them correctly.…”