More Like this

1. Patterns of Gender-Specializing Query Reformulation

   Raj, Amifa; Mitra, Bhaksar; Ekstrand, Michael D.; Craswell, Nick (July 2023, Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR ’23))

   Users of search systems often reformulate their queries by adding query terms to reflect their evolving information need or to more precisely express their information need when the system fails to surface relevant content. Analyzing these query reformulations can inform us about both system and user behavior. In this work, we study a special category of query reformulations that involve specifying demographic group attributes, such as gender, as part of the reformulated query (e.g., “olympic 2021 soccer results” → “olympic 2021 women‘s soccer results”). There are many ways a query, the search results, and a demographic attribute such as gender may relate, leading us to hypothesize different causes for these reformulation patterns, such as under-representation on the original result page or based on the linguistic theory of markedness. This paper reports on an observational study of gender-specializing query reformulations—their contexts and effects—as a lens on the relationship between system results and gender, based on large-scale search log data from Bing. We find that these reformulations sometimes correct for and other times reinforce gender representation on the original result page, but typically yield better access to the ultimately-selected results. The prevalence of these reformulations—and which gender they skew towards—differ by topical context. However, we do not find evidence that either group under-representation or markedness alone adequately explains these reformulations. We hope that future research will use such reformulations as a probe for deeper investigation into gender (and other demographic) representation on the search result page. 

   more » « less
2. Synthesizing 3D Shapes From Silhouette Image Collections Using Multi-Projection Generative Adversarial Networks

   https://doi.org/10.1109/CVPR.2019.00568  

   Li, Xiao; Dong, Yue; Peers, Pieter; Tong, Xin (June 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR))

   We present a new weakly supervised learning-based method for generating novel category-specific 3D shapes from unoccluded image collections. Our method is weakly supervised and only requires silhouette annotations from unoccluded, category-specific objects. Our method does not require access to the object's 3D shape, multiple observations per object from different views, intra-image pixel correspondences, or any view annotations. Key to our method is a novel multi-projection generative adversarial network (MP-GAN) that trains a 3D shape generator to be consistent with multiple 2D projections of the 3D shapes, and without direct access to these 3D shapes. This is achieved through multiple discriminators that encode the distribution of 2D projections of the 3D shapes seen from a different views. Additionally, to determine the view information for each silhouette image, we also train a view prediction network on visualizations of 3D shapes synthesized by the generator. We iteratively alternate between training the generator and training the view prediction network. We validate our multi-projection GAN on both synthetic and real image datasets. Furthermore, we also show that multi-projection GANs can aid in learning other high-dimensional distributions from lower dimensional training datasets, such as material-class specific spatially varying reflectance properties from images. 

   more » « less
3. Robust Query Driven Cardinality Estimation under Changing Workloads

   https://doi.org/10.14778/3583140.3583164  

   Negi, Parimarjan; Wu, Ziniu; Kipf, Andreas; Tatbul, Nesime; Marcus, Ryan; Madden, Sam; Kraska, Tim; Alizadeh, Mohammad (February 2023, Proceedings of the VLDB Endowment)

   Query driven cardinality estimation models learn from a historical log of queries. They are lightweight, having low storage requirements, fast inference and training, and are easily adaptable for any kind of query. Unfortunately, such models can suffer unpredictably bad performance under workload drift, i.e., if the query pattern or data changes. This makes them unreliable and hard to deploy. We analyze the reasons why models become unpredictable due to workload drift, and introduce modifications to the query representation and neural network training techniques to make query-driven models robust to the effects of workload drift. First, we emulate workload drift in queries involving some unseen tables or columns by randomly masking out some table or column features during training. This forces the model to make predictions with missing query information, relying more on robust features based on up-to-date DBMS statistics that are useful even when query or data drift happens. Second, we introduce join bitmaps, which extends sampling-based features to be consistent across joins using ideas from sideways information passing. Finally, we show how both of these ideas can be adapted to handle data updates. We show significantly greater generalization than past works across different workloads and databases. For instance, a model trained with our techniques on a simple workload (JOBLight-train), with 40ksynthetically generated queries of at most 3 tables each, is able to generalize to the much more complex Join Order Benchmark, which include queries with up to 16 tables, and improve query runtimes by 2× over PostgreSQL. We show similar robustness results with data updates, and across other workloads. We discuss the situations where we expect, and see, improvements, as well as more challenging workload drift scenarios where these techniques do not improve much over PostgreSQL. However, even in the most challenging scenarios, our models never perform worse than PostgreSQL, while standard query driven models can get much worse than PostgreSQL. 

   more » « less
4. Multi-level Partition of Unity on Differentiable Moving Particles

   https://doi.org/10.1145/3687989  

   He, Jinjin; Zhang, Taiyuan; Kobayashi, Hiroki; Kawamoto, Atsushi; Zhou, Yuqing; Nomura, Tsuyoshi; Zhu, Bo (November 2024, ACM Transactions on Graphics)

   We introduce a differentiable moving particle representation based on the multi-level partition of unity (MPU) to represent dynamic implicit geometries. At the core of our representation are two groups of particles, named feature particles and sample particles, which can move in space and produce dynamic surfaces according to external velocity fields or optimization gradients. These two particle groups iteratively guide and correct each other by alternating their roles as inputs and outputs. Each feature particle carries a set of coefficients for a local quadratic patch. These particle patches are assembled with partition-of-unity weights to derive a continuous implicit global shape. Each sampling particle carries its position and orientation, serving as dense surface samples for optimization tasks. Based on these moving particles, we develop a fully differentiable framework to infer and evolve highly detailed implicit geometries, enhanced by a multi-level background grid for particle adaptivity, across different inverse tasks. We demonstrated the efficacy of our representation through various benchmark comparisons with state-of-the-art neural representations, achieving lower memory consumption, fewer training iterations, and orders of magnitude higher accuracy in handling topologically complex objects and dynamic tracking tasks. 

   more » « less
5. To switch or not to switch – a machine learning approach for ferroelectricity

   https://doi.org/10.1039/c9na00731h  

   Neumayer, Sabine M.; Jesse, Stephen; Velarde, Gabriel; Kholkin, Andrei L.; Kravchenko, Ivan; Martin, Lane W.; Balke, Nina; Maksymovych, Peter (May 2020, Nanoscale Advances)

   null (Ed.)

   With the advent of increasingly elaborate experimental techniques in physics, chemistry and materials sciences, measured data are becoming bigger and more complex. The observables are typically a function of several stimuli resulting in multidimensional data sets spanning a range of experimental parameters. As an example, a common approach to study ferroelectric switching is to observe effects of applied electric field, but switching can also be enacted by pressure and is influenced by strain fields, material composition, temperature, time, etc. Moreover, the parameters are usually interdependent, so that their decoupling toward univariate measurements or analysis may not be straightforward. On the other hand, both explicit and hidden parameters provide an opportunity to gain deeper insight into the measured properties, provided there exists a well-defined path to capture and analyze such data. Here, we introduce a new, two-dimensional approach to represent hysteretic response of a material system to applied electric field. Utilizing ferroelectric polarization as a model hysteretic property, we demonstrate how explicit consideration of electromechanical response to two rather than one control voltages enables significantly more transparent and robust interpretation of observed hysteresis, such as differentiating between charge trapping and ferroelectricity. Furthermore, we demonstrate how the new data representation readily fits into a variety of machine-learning methodologies, from unsupervised classification of the origins of hysteretic response via linear clustering algorithms to neural-network-based inference of the sample temperature based on the specific morphology of hysteresis. 

   more » « less