Recent advances in large language models have demonstrated remarkable effectiveness in information retrieval (IR) tasks. While many neural IR systems encode queries and documents into single-vector representations, multi-vector models elevate the retrieval quality by producing multi-vector representations and facilitating similarity searches at the granularity of individual tokens. However, these models significantly amplify memory and storage requirements for retrieval indices by an order of magnitude. This escalation in index size renders the scalability of multi-vector IR models progressively challenging due to their substantial memory demands. We introduce Embedding from Storage Pipelined Network (ESPN) where we offload the entire re-ranking embedding tables to SSDs and reduce the memory requirements by 5-16x. We design a software prefetcher with hit rates exceeding 90%, improving SSD based retrieval up to 6.4x, and demonstrate that we can maintain near memory levels of query latency even for large query batch sizes.

This paper focuses on using natural language descriptions to enhance predictive models in the chemistry field. Conventionally, chemoinformatics models are trained with extensive structured data manually extracted from the literature. In this paper, we introduce TextReact, a novel method that directly augments predictive chemistry with texts retrieved from the literature. TextReact retrieves text descriptions relevant for a given chemical reaction, and then aligns them with the molecular representation of the reaction. This alignment is enhanced via an auxiliary masked LM objective incorporated in the predictor training. We empirically validate the framework on two chemistry tasks: reaction condition recommendation and one-step retrosynthesis. By leveraging text retrieval, TextReact significantly outperforms state-of-the-art chemoinformatics models trained solely on molecular data.

Calibrating agent-based models (ABMs) in economics and finance typically involves a derivative-free search in a very large parameter space. In this work, we benchmark a number of search methods in the calibration of a well-known macroeconomic ABM on real data, and further assess the performance of "mixed strategies" made by combining different methods. We find that methods based on random-forest surrogates are particularly efficient, and that combining search methods generally increases performance since the biases of any single method are mitigated. Moving from these observations, we propose a reinforcement learning (RL) scheme to automatically select and combine search methods on-the-fly during a calibration run. The RL agent keeps exploiting a specific method only as long as this keeps performing well, but explores new strategies when the specific method reaches a performance plateau. The resulting RL search scheme outperforms any other method or method combination tested, and does not rely on any prior information or trial and error procedure.

Self-driving laboratories (SDLs) consist of multiple stations that perform material synthesis and characterisation tasks. To minimize station downtime and maximize experimental throughput, it is practical to run experiments in asynchronous parallel, in which multiple experiments are being performed at once in different stages. Asynchronous parallelization of experiments, however, introduces delayed feedback (i.e. "pending experiments"), which is known to reduce Bayesian optimiser performance. Here, we build a simulator for a multi-stage SDL and compare optimisation strategies for dealing with delayed feedback and asynchronous parallelized operation. Using data from a real SDL, we build a ground truth Bayesian optimisation simulator from 177 previously run experiments for maximizing the conductivity of functional coatings. We then compare search strategies such as expected improvement, noisy expected improvement, 4-mode exploration and random sampling. We evaluate their performance in terms of amount of delay and problem dimensionality. Our simulation results showcase the trade-off between the asynchronous parallel operation and delayed feedback.

Recently, the growing memory demands of embedding tables in Deep Learning Recommendation Models (DLRMs) pose great challenges for model training and deployment. Existing embedding compression solutions cannot simultaneously meet three key design requirements: memory efficiency, low latency, and adaptability to dynamic data distribution. This paper presents CAFE, a Compact, Adaptive, and Fast Embedding compression framework that addresses the above requirements. The design philosophy of CAFE is to dynamically allocate more memory resources to important features (called hot features), and allocate less memory to unimportant ones. In CAFE, we propose a fast and lightweight sketch data structure, named HotSketch, to capture feature importance and report hot features in real time. For each reported hot feature, we assign it a unique embedding. For the non-hot features, we allow multiple features to share one embedding by using hash embedding technique. Guided by our design philosophy, we further propose a multi-level hash embedding framework to optimize the embedding tables of non-hot features. We theoretically analyze the accuracy of HotSketch, and analyze the model convergence against deviation. Extensive experiments show that CAFE significantly outperforms existing embedding compression methods, yielding 3.92% and 3.68% superior testing AUC on Criteo Kaggle dataset and CriteoTB dataset at a compression ratio of 10000x. The source codes of CAFE are available at GitHub.

E-commerce search and recommendation usually operate on structured data such as product catalogs and taxonomies. However, creating better search and recommendation systems often requires a large variety of unstructured data including customer reviews and articles on the web. Traditionally, the solution has always been converting unstructured data into structured data through information extraction, and conducting search over the structured data. However, this is a costly approach that often has low quality. In this paper, we envision a solution that does entirely the opposite. Instead of converting unstructured data (web pages, customer reviews, etc) to structured data, we instead convert structured data (product inventory, catalogs, taxonomies, etc) into textual data, which can be easily integrated into the text corpus that trains LLMs. Then, search and recommendation can be performed through a Q/A mechanism through an LLM instead of using traditional information retrieval methods over structured data.

In this work, we approach the problem of Qur'anic information retrieval (IR) in Arabic and English. Using the latest state-of-the-art methods in neural IR, we research what helps to tackle this task more efficiently. Training retrieval models requires a lot of data, which is difficult to obtain for training in-domain. Therefore, we commence with training on a large amount of general domain data and then continue training on in-domain data. To handle the lack of in-domain data, we employed a data augmentation technique, which considerably improved results in MRR@10 and NDCG@5 metrics, setting the state-of-the-art in Qur'anic IR for both English and Arabic. The absence of an Islamic corpus and domain-specific model for IR task in English motivated us to address this lack of resources and take preliminary steps of the Islamic corpus compilation and domain-specific language model (LM) pre-training, which helped to improve the performance of the retrieval models that use the domain-specific LM as the shared backbone. We examined several language models (LMs) in Arabic to select one that efficiently deals with the Qur'anic IR task. Besides transferring successful experiments from English to Arabic, we conducted additional experiments with retrieval task in Arabic to amortize the scarcity of general domain datasets used to train the retrieval models. Handling Qur'anic IR task combining English and Arabic allowed us to enhance the comparison and share valuable insights across models and languages.

Image search is an essential and user-friendly method to explore vast galleries of digital images. However, existing image search methods heavily rely on proximity measurements like tag matching or image similarity, requiring precise user inputs for satisfactory results. To meet the growing demand for a contemporary image search engine that enables accurate comprehension of users' search intentions, we introduce an innovative user intent expansion framework. Our framework leverages visual-language models to parse and compose multi-modal user inputs to provide more accurate and satisfying results. It comprises two-stage processes: 1) a parsing stage that incorporates a language parsing module with large language models to enhance the comprehension of textual inputs, along with a visual parsing module that integrates an interactive segmentation module to swiftly identify detailed visual elements within images; and 2) a logic composition stage that combines multiple user search intents into a unified logic expression for more sophisticated operations in complex searching scenarios. Moreover, the intent expansion framework enables users to perform flexible contextualized interactions with the search results to further specify or adjust their detailed search intents iteratively. We implemented the framework into an image search system for NFT (non-fungible token) search and conducted a user study to evaluate its usability and novel properties. The results indicate that the proposed framework significantly improves users' image search experience. Particularly the parsing and contextualized interactions prove useful in allowing users to express their search intents more accurately and engage in a more enjoyable iterative search experience.

Information retrieval in real-time search presents unique challenges distinct from those encountered in classical web search. These challenges are particularly pronounced due to the rapid change of user search intent, which is influenced by the occurrence and evolution of breaking news events, such as earthquakes, elections, and wars. Previous dense retrieval methods, which primarily focused on static semantic representation, lack the capacity to capture immediate search intent, leading to inferior performance in retrieving the most recent event-related documents in time-sensitive scenarios. To address this issue, this paper expands the query with event information that represents real-time search intent. The Event information is then integrated with the query through a cross-attention mechanism, resulting in a time-context query representation. We further enhance the model's capacity for event representation through multi-task training. Since publicly available datasets such as MS-MARCO do not contain any event information on the query side and have few time-sensitive queries, we design an automatic data collection and annotation pipeline to address this issue, which includes ModelZoo-based Coarse Annotation and LLM-driven Fine Annotation processes. In addition, we share the training tricks such as two-stage training and hard negative sampling. Finally, we conduct a set of offline experiments on a million-scale production dataset to evaluate our approach and deploy an A/B testing in a real online system to verify the performance. Extensive experimental results demonstrate that our proposed approach significantly outperforms existing state-of-the-art baseline methods.

Collecting data, extracting value, and combining insights from relational and context-rich multi-modal sources in data processing pipelines presents a challenge for traditional relational DBMS. While relational operators allow declarative and optimizable query specification, they are limited to data transformations unsuitable for capturing or analyzing context. On the other hand, representation learning models can map context-rich data into embeddings, allowing machine-automated context processing but requiring imperative data transformation integration with the analytical query. To bridge this dichotomy, we present a context-enhanced relational join and introduce an embedding operator composable with relational operators. This enables hybrid relational and context-rich vector data processing, with algebraic equivalences compatible with relational algebra and corresponding logical and physical optimizations. We investigate model-operator interaction with vector data processing and study the characteristics of the E-join operator. Using an example of string embeddings, we demonstrate enabling hybrid context-enhanced processing on relational join operators with vector embeddings. The importance of holistic optimization, from logical to physical, is demonstrated in an order of magnitude execution time improvement.