Federated learning is a decentralized framework that enables client participation in collaborative learning without centralized data collection. However, the framework is susceptible to suboptimal model convergence induced by heterogeneity among the client datasets. These discrepancies, including label imbalance, dissimilarity in data distributions, and uneven data volumes between clients, may cause disagreements among local client updates, affecting the ability of the global model to converge effectively during aggregation. We suggest that one potential solution to this problem lies in weighting the model aggregation by client importance and client-to-client relationships. Based on this idea, we propose HyperGenFL (HG-FL), a hypernetwork that generates aggregation weights from learnable client embeddings without requiring any training or benchmarking data. HG-FL utilizes the attention mechanism to capture inter-client relationships based on learnable client-specific embeddings in order to generate model aggregation weights dynamically during federated learning. By guiding the aggregation process with these learnable relationships between local models, HG-FL reduces update conflicts and improves global model performance. We assess HG-FL under various data-heterogeneous environments based on different benchmark datasets including Fashion-MNIST, CIFAR10, CIFAR100 and Tiny-ImageNet. Experimental results demonstrate that HG-FL can achieve superior performance over a range of existing baseline methods under challenging cases with various heterogeneous environments, large models and a large number of clients.

Nested Named Entity Recognition (NNER), as a subarea of Named Entity Recognition, has presented longstanding challenges to researchers. In NNER, one entity may be part of a larger entity, which can occur at multiple levels. These nested structures prevent traditional sequence labeling methods from properly recognizing all entities. While recent research has focused on designing better recognition methods for NNER in various languages, Chinese Nested Named Entity Recognition (CNNER) is still underdeveloped, largely due to a lack of freely available CNNER benchmarks. To support CNNER research, in this paper, we introduce ChiNesE, a CNNER dataset comprising 20,000 sentences from online passages in multiple domains and containing 117,284 entities that fall into 10 categories, of which 43.8% are nested named entities. Based on ChiNesE, we propose Mulco, a novel method that can recognize named entities in nested structures through multiple scopes. Each scope uses a scope-based sequence labeling method that predicts an anchor and the length of a named entity to recognize it. Experimental results show that Mulco outperforms state-of-the-art baseline methods with different recognition schemes on ChiNesE and ACE 2005 Chinese corpus.

Machine learning has been a popular tool in many different fields, including procedural content generation. However, procedural content generation via machine learning (PCGML) approaches can struggle with controllability and coherence. In this paper, we attempt to address these problems by learning to generate human-like paths, and then generating levels based on these paths. We extract player path data from gameplay video, train an LSTM to generate new paths based on this data, and then generate game levels based on this path data. We demonstrate that our approach leads to more coherent levels for the game Lode Runner in comparison to an existing PCGML approach.

Search indices are fundamental building blocks of many systems, and there is great interest in running them on encrypted data. Unfortunately, many known schemes that enable search queries on encrypted data achieve efficiency at the expense of security, as they reveal access patterns to the encrypted data. In this paper we present Oblix, a search index for encrypted data that is oblivious (provably hides access patterns), is dynamic (supports inserts and deletes), and has good efficiency. Oblix relies on a combination of novel oblivious-access techniques and recent hardware enclave platforms (e.g., Intel SGX). In particular, a key technical contribution is the design and implementation of doubly-oblivious data structures, in which the client's accesses to its internal memory are oblivious, in addition to accesses to its external memory at the server. These algorithms are motivated by hardware enclaves like SGX, which leak access patterns to both internal and external memory. We demonstrate the usefulness of Oblix in several applications: private contact discovery for Signal, private retrieval of public keys for Key Transparency, and searchable encryption that hides access patterns and result sizes.

We present a novel approach for latency-tolerant delivery of visualization and rendering results where client-side frame rate display performance is independent of source dataset size, image size, visualization technique or rendering complexity. Our approach delivers pre-rendered, multiresolution images to a remote user as they navigate through different viewpoints, visualization or rendering parameters. We employ demand-driven tiled, multiresolution image streaming and prefetching to efficiently utilize available bandwidth while providing the maximum resolution user can perceive from a given viewpoint. Since image data is the only input to our system, our approach is generally applicable to all visualization and graphics rendering applications capable of generating image files in an ordered fashion. In our implementation, a normal web server provides on-demand images to a remote custom client application, which uses client-pull to obtain and cache only those images required to fulfill the interaction needs. The main contributions of this work are: (1) an architecture for latency-tolerant, remote delivery of precomputed imagery suitable for use with any visualization or rendering application capable of producing images in an ordered fashion; (2) a performance study showing the impact of diverse network environments and different tunable system parameters on end-to-end system performance in terms of deliverable frames per second.