More Like this

1. Proxy Re-Encryption and Re-Signatures from Lattices

   https://doi.org/https://doi.org/10.1007/978-3-030-21568-2_18  

   Fan, Xiong; Liu, Feng-Hao (May 2019, International Conference on Applied Cryptography and Network Security)
2. Re-ranking via Metric Fusion for Object Retrieval and Person Re-identification.

   Bai, Song; Tang, Peng; Torr, Philip; Latecki, Longin Jan (June 2019, IEEE Conference on Computer Vision and Pattern Recognition)

   This work studies the unsupervised re-ranking procedure for object retrieval and person re-identification with a specific concentration on an ensemble of multiple metrics (or similarities). While the re-ranking step is involved by running a diffusion process on the underlying data manifolds, thefusionstepcanleveragethecomplementarityofmultiple metrics. We give a comprehensive summary of existing fusion with diffusion strategies, and systematically analyze their pros and cons. Based on the analysis, we propose a unified yet robust algorithm which inherits their advantages and discards their disadvantages. Hence, we call it Unified Ensemble Diffusion (UED). More interestingly, we derive that the inherited properties indeed stem from a theoretical framework, where the relevant works can be elegantly summarized as special cases of UED by imposing additional constraints on the objective function and varying the solver of similarity propagation. Extensive experiments with 3D shape retrieval, image retrieval and person re-identification demonstrate that the proposed framework outperforms the state of the arts, and at the same time suggest that re-ranking via metric fusion is a promising tool to further improve the retrieval performance of existing algorithms. 

   more » « less
3. Long Document Re-ranking with Modular Re-ranker

   https://doi.org/10.1145/3477495.3531860  

   Gao, Luyu; Callan, Jamie (July 2022, ACM)

   Long document re-ranking has been a challenging problem for neural re-rankers based on deep language models like BERT. Early work breaks the documents into short passage-like chunks. These chunks are independently mapped to scalar scores or latent vectors, which are then pooled into a final relevance score. These encode-and-pool methods however inevitably introduce an information bottleneck: the low dimension representations. In this paper, we propose instead to model full query-to-document interaction, leveraging the attention operation and modular Transformer re-ranker framework. First, document chunks are encoded independently with an encoder module. An interaction module then encodes the query and performs joint attention from the query to all document chunk representations. We demonstrate that the model can use this new degree of freedom to aggregate important information from the entire document. Our experiments show that this design produces effective re-ranking on two classical IR collections Robust04 and ClueWeb09, and a large-scale supervised collection MS-MARCO document ranking. CCS CONCEPTS • Information systems 

   more » « less
4. RE-WIND: Architectural Design Studio and the Re-Purposing of Wind Turbine Blades

   Morrow, R.; Gentry, R.; Al-Haddad, T. (September 2018, SEEDS 2018: Sustainable Ecological Engineering Design for Society)

   This paper discusses the opening moves of an international multidisciplinary research project involving researchers from Ireland, Northern Ireland and the US, aiming to address the global problem of end-of-life disposal of wind turbine blades. The problem is one of enormous scale on several levels: a typical 2.0 MW turbine has three 50m long blades containing around 20 tonnes of fibre reinforced plastic (FRP). It is estimated that by 2050, 39.8 million tonnes of material from the global wind industry will await disposal. Whilst land-fill is the current means of disposal, the nature of the materials used in the composite construction of wind blades (glass and carbon fibres, resins, foams) means it unsustainable. Hence, the project sets out to deploy innovative design and logistical concepts for reusing and recycling these blades. The project begins within an innovative joint design studio, staged between Queen’s University Belfast and the Georgia Institute of Technology, where architecture students will, within the highly-constrained contexts of the blade properties and the potential reuse sites, systematically generate, filter, and prototype a selection of proposals, reusing the decommissioned wind turbine blades in buildings, infrastructure, landscape, and public art. The paper analyzes the potential and challenges of considering this highly constrained and yet multidisciplinary problem within the context of a Masters level Architecture studio. The paper concludes with an analysis of how outcome-driven design problems challenge traditional design studio cultures, acknowledging the need to make processes and ideas more explicit in order to categorise, analyse, rank and refine proposed architectural solutions. 

   more » « less
5. Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals

   Dan, T; Ding, J; Wei, Z; Kovalsky, S; Kim, M; Kim, WH; Wu, G (September 2023, Advances in Neural Information Processing Systems 36 (NeurIPS 2023))

   Graphs are ubiquitous in various domains, such as social networks and biological systems. Despite the great successes of graph neural networks (GNNs) in modeling and analyzing complex graph data, the inductive bias of locality assumption, which involves exchanging information only within neighboring connected nodes, restricts GNNs in capturing long-range dependencies and global patterns in graphs. Inspired by the classic Brachistochrone problem, we seek how to devise a new inductive bias for cutting-edge graph application and present a general framework through the lens of variational analysis. The backbone of our framework is a two-way mapping between the discrete GNN model and continuous diffusion functional, which allows us to design application-specific objective function in the continuous domain and engineer discrete deep model with mathematical guarantees. First, we address over-smoothing in current GNNs. Specifically, our inference reveals that the existing layer-by-layer models of graph embedding learning are equivalent to a ℓ 2 -norm integral functional of graph gradients, which is the underlying cause of the over-smoothing problem. Similar to edge-preserving filters in image denoising, we introduce the total variation (TV) to promote alignment of the graph diffusion pattern with the global information present in community topologies. On top of this, we devise a new selective mechanism for inductive bias that can be easily integrated into existing GNNs and effectively address the trade-off between model depth and over-smoothing. Second, we devise a novel generative adversarial network (GAN) to predict the spreading flows in the graph through a neural transport equation. To avoid the potential issue of vanishing flows, we tailor the objective function to minimize the transportation within each community while maximizing the inter-community flows. Our new GNN models achieve state-of-the-art (SOTA) performance on graph learning benchmarks such as Cora, Citeseer, and Pubmed. 

   more » « less