SEA: The WebConf Edition
In this edition of SEA we will learn about two papers that were recently published at the Web Conference 2021. We have two amazing speakers lined up: Daniel Daza from the Vrije Universiteit Amsterdam and Honglei Zhuang from Google Research.
*** IMPORTANT: Make sure to (1) attend the meetup on the meetup page and (2) ensure you receive emails from Meetup. Shortly before the event we will send you the Zoom link and password to attend, as well as the info you need to log in via the browser (if your organisation does not allow you to install Zoom). You will only receive this if you have done both these steps. ***
** 17:00 - 17:30 - Daniel Daza, Vrije Universiteit Amsterdam **
Title: Inductive Entity Representations from Text via Link Prediction
Abstract: Knowledge Graphs are of vital importance for multiple applications on the web, including information retrieval, recommender systems, and metadata annotation. Regardless of whether they are built manually by domain experts or with automatic pipelines, such graphs are often incomplete. While some machine learning methods have been proposed to address this issue, many of them ignore properties like entity descriptions, and are limited to predictions involving entities in the training set.
In this talk, I will introduce our recently proposed method for link prediction over knowledge graphs where entities have an associated textual description. I will then describe our experimental framework and discuss how such a method enables learning representations of entities that are not limited to link prediction in the graph, but also to other tasks like entity classification and information retrieval.
**17:30 - 18:00 Honglei Zhuang, Google Research **
Title: Cross-Positional Attention for Debiasing Clicks
Abstract: A well-known challenge in leveraging implicit user feedback like clicks to improve real-world search services and recommender systems is its inherent bias. Most existing click models are based on the examination hypothesis in user behaviors and differ in how to model such an examination bias. However, they are constrained by assuming a simple position-based bias or enforcing a sequential order in user examination behaviors. These assumptions are insufficient to capture complex real-world user behaviors and hardly generalize to modern user interfaces (UI) in web applications (e.g., results shown in a grid view). In this work, we propose a fully data-driven neural model for the examination bias, Cross-Positional Attention (XPA), which is more flexible in fitting complex user behaviors. Our model leverages the attention mechanism to effectively capture cross-positional interactions among displayed items and is applicable to arbitrary UIs. We employ XPA in a novel neural click model that can both predict clicks and estimate relevance. Our experiments on offline synthetic data sets show that XPA is robust among different click generation processes. We further apply XPA to a large-scale real-world recommender system, showing significantly better results than baselines in online A/B experiments that involve millions of users. This validates the necessity to model more complex user behaviors than those proposed in the literature.
After the two talks we will leave the Zoom call open for another half an hour, for any remaining questions. This always results in a nice discussion!