Hybrid Preference Optimization: Augmenting Direct Preference Optimization with Auxiliary Objectives

For aligning large language models (LLMs), prior work has leveraged reinforcement learning via human feedback (RLHF) or variations of direct preference optimization (DPO). While DPO offers a simpler framework based on maximum likelihood estimation, it compromises on the ability to tune language models to easily maximize non-differentiable and non-binary objectives according to the LLM designer's preferences (e.g., using simpler language or minimizing specific kinds of harmful content). These may neither align with user preferences nor even be able to be captured tractably by binary preference data. To leverage the simplicity and performance of DPO with the generalizability of RL, we propose a hybrid approach between DPO and RLHF. With a simple augmentation to the implicit reward decomposition of DPO, we allow for tuning LLMs to maximize a set of arbitrary auxiliary rewards using offline RL. The proposed method, Hybrid Preference Optimization (HPO), shows the ability to effectively generalize to both user preferences and auxiliary designer objectives, while preserving alignment performance across a range of challenging benchmarks and model sizes.

OmniSearchSage: Multi-Task Multi-Entity Embeddings for Pinterest Search

In this paper, we present OmniSearchSage, a versatile and scalable system for understanding search queries, pins, and products for Pinterest search. We jointly learn a unified query embedding coupled with pin and product embeddings, leading to an improvement of $>8\%$ relevance, $>7\%$ engagement, and $>5\%$ ads CTR in Pinterest's production search system. The main contributors to these gains are improved content understanding, better multi-task learning, and real-time serving. We enrich our entity representations using diverse text derived from image captions from a generative LLM, historical engagement, and user-curated boards. Our multitask learning setup produces a single search query embedding in the same space as pin and product embeddings and compatible with pre-existing pin and product embeddings. We show the value of each feature through ablation studies, and show the effectiveness of a unified model compared to standalone counterparts. Finally, we share how these embeddings have been deployed across the Pinterest search stack, from retrieval to ranking, scaling to serve $300k$ requests per second at low latency. Our implementation of this work is available at https://github.com/pinterest/atg-research/tree/main/omnisearchsage.

Rethinking Personalized Ranking at Pinterest: An End-to-End Approach

In this work, we present our journey to revolutionize the personalized recommendation engine through end-to-end learning from raw user actions. We encode user's long-term interest in Pinner- Former, a user embedding optimized for long-term future actions via a new dense all-action loss, and capture user's short-term intention by directly learning from the real-time action sequences. We conducted both offline and online experiments to validate the performance of the new model architecture, and also address the challenge of serving such a complex model using mixed CPU/GPU setup in production. The proposed system has been deployed in production at Pinterest and has delivered significant online gains across organic and Ads applications.

Evolution of a Web-Scale Near Duplicate Image Detection System

Detecting near duplicate images is fundamental to the content ecosystem of photo sharing web applications. However, such a task is challenging when involving a web-scale image corpus containing billions of images. In this paper, we present an efficient system for detecting near duplicate images across 8 billion images. Our system consists of three stages: candidate generation, candidate selection, and clustering. We also demonstrate that this system can be used to greatly improve the quality of recommendations and search results across a number of real-world applications. In addition, we include the evolution of the system over the course of six years, bringing out experiences and lessons on how new systems are designed to accommodate organic content growth as well as the latest technology. Finally, we are releasing a human-labeled dataset of ~53,000 pairs of images introduced in this paper.

Visual Search at Pinterest

We demonstrate that, with the availability of distributed computation platforms such as Amazon Web Services and open-source tools, it is possible for a small engineering team to build, launch and maintain a cost-effective, large-scale visual search system with widely available tools. We also demonstrate, through a comprehensive set of live experiments at Pinterest, that content recommendation powered by visual search improve user engagement. By sharing our implementation details and the experiences learned from launching a commercial visual search engines from scratch, we hope visual search are more widely incorporated into today's commercial applications.

Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images

In this paper, we focus on training and evaluating effective word embeddings with both text and visual information. More specifically, we introduce a large-scale dataset with 300 million sentences describing over 40 million images crawled and downloaded from publicly available Pins (i.e. an image with sentence descriptions uploaded by users) on Pinterest. This dataset is more than 200 times larger than MS COCO, the standard large-scale image dataset with sentence descriptions. In addition, we construct an evaluation dataset to directly assess the effectiveness of word embeddings in terms of finding semantically similar or related words and phrases. The word/phrase pairs in this evaluation dataset are collected from the click data with millions of users in an image search system, thus contain rich semantic relationships. Based on these datasets, we propose and compare several Recurrent Neural Networks (RNNs) based multimodal (text and image) models. Experiments show that our model benefits from incorporating the visual information into the word embeddings, and a weight sharing strategy is crucial for learning such multimodal embeddings. The project page is: http://www.stat.ucla.edu/~junhua.mao/multimodal_embedding.html

A Hybrid Method for Distance Metric Learning

We consider the problem of learning a measure of distance among vectors in a feature space and propose a hybrid method that simultaneously learns from similarity ratings assigned to pairs of vectors and class labels assigned to individual vectors. Our method is based on a generative model in which class labels can provide information that is not encoded in feature vectors but yet relates to perceived similarity between objects. Experiments with synthetic data as well as a real medical image retrieval problem demonstrate that leveraging class labels through use of our method improves retrieval performance significantly.