Variational Multi-Modal Hypergraph Attention Network for Multi-Modal Relation Extraction

Multi-modal relation extraction (MMRE) is a challenging task that aims to identify relations between entities in text leveraging image information. Existing methods are limited by their neglect of the multiple entity pairs in one sentence sharing very similar contextual information (ie, the same text and image), resulting in increased difficulty in the MMRE task. To address this limitation, we propose the Variational Multi-Modal Hypergraph Attention Network (VM-HAN) for multi-modal relation extraction. Specifically, we first construct a multi-modal hypergraph for each sentence with the corresponding image, to establish different high-order intra-/inter-modal correlations for different entity pairs in each sentence. We further design the Variational Hypergraph Attention Networks (V-HAN) to obtain representational diversity among different entity pairs using Gaussian distribution and learn a better hypergraph structure via variational attention. VM-HAN achieves state-of-the-art performance on the multi-modal relation extraction task, outperforming existing methods in terms of accuracy and efficiency.

FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression

Nanosatellite constellations equipped with sensors capturing large geographic regions provide unprecedented opportunities for Earth observation. As constellation sizes increase, network contention poses a downlink bottleneck. Orbital Edge Computing (OEC) leverages limited onboard compute resources to reduce transfer costs by processing the raw captures at the source. However, current solutions have limited practicability due to reliance on crude filtering methods or over-prioritizing particular downstream tasks. This work presents FOOL, an OEC-native and task-agnostic feature compression method that preserves prediction performance. FOOL partitions high-resolution satellite imagery to maximize throughput. Further, it embeds context and leverages inter-tile dependencies to lower transfer costs with negligible overhead. While FOOL is a feature compressor, it can recover images with competitive scores on perceptual quality measures at lower bitrates. We extensively evaluate transfer cost reduction by including the peculiarity of intermittently available network connections in low earth orbit. Lastly, we test the feasibility of our system for standardized nanosatellite form factors. We demonstrate that FOOL permits downlinking over 100x the data volume without relying on prior information on the downstream tasks.

Towards Effective Next POI Prediction: Spatial and Semantic Augmentation with Remote Sensing Data

The next point-of-interest (POI) prediction is a significant task in location-based services, yet its complexity arises from the consolidation of spatial and semantic intent. This fusion is subject to the influences of historical preferences, prevailing location, and environmental factors, thereby posing significant challenges. In addition, the uneven POI distribution further complicates the next POI prediction procedure. To address these challenges, we enrich input features and propose an effective deep-learning method within a two-step prediction framework. Our method first incorporates remote sensing data, capturing pivotal environmental context to enhance input features regarding both location and semantics. Subsequently, we employ a region quad-tree structure to integrate urban remote sensing, road network, and POI distribution spaces, aiming to devise a more coherent graph representation method for urban spatial. Leveraging this method, we construct the QR-P graph for the user's historical trajectories to encapsulate historical travel knowledge, thereby augmenting input features with comprehensive spatial and semantic insights. We devise distinct embedding modules to encode these features and employ an attention mechanism to fuse diverse encodings. In the two-step prediction procedure, we initially identify potential spatial zones by predicting user-preferred tiles, followed by pinpointing specific POIs of a designated type within the projected tiles. Empirical findings from four real-world location-based social network datasets underscore the remarkable superiority of our proposed approach over competitive baseline methods.

Context-based Fast Recommendation Strategy for Long User Behavior Sequence in Meituan Waimai

In the recommender system of Meituan Waimai, we are dealing with ever-lengthening user behavior sequences, which pose an increasing challenge to modeling user preference effectively. Existing sequential recommendation models often fail to capture long-term dependencies or are too complex, complicating the fulfillment of Meituan Waimai's unique business needs. To better model user interests, we consider selecting relevant sub-sequences from users' extensive historical behaviors based on their preferences. In this specific scenario, we've noticed that the contexts in which users interact have a significant impact on their preferences. For this purpose, we introduce a novel method called Context-based Fast Recommendation Strategy to tackle the issue of long sequences. We first identify contexts that share similar user preferences with the target context and then locate the corresponding PoIs based on these identified contexts. This approach eliminates the necessity to select a sub-sequence for every candidate PoI, thereby avoiding high time complexity. Specifically, we implement a prototype-based approach to pinpoint contexts that mirror similar user preferences. To amplify accuracy and interpretability, we employ JS divergence of PoI attributes such as categories and prices as a measure of similarity between contexts. A temporal graph integrating both prototype and context nodes helps incorporate temporal information. We then identify appropriate prototypes considering both target contexts and short-term user preferences. Following this, we utilize contexts aligned with these prototypes to generate a sub-sequence, aimed at predicting CTR and CTCVR scores with target attention. Since its inception in 2023, this strategy has been adopted in Meituan Waimai's display recommender system, leading to a 4.6% surge in CTR and a 4.2% boost in GMV.

FedRDMA: Communication-Efficient Cross-Silo Federated LLM via Chunked RDMA Transmission

Communication overhead is a significant bottleneck in federated learning (FL), which has been exaggerated with the increasing size of AI models. In this paper, we propose FedRDMA, a communication-efficient cross-silo FL system that integrates RDMA into the FL communication protocol. To overcome the limitations of RDMA in wide-area networks (WANs), FedRDMA divides the updated model into chunks and designs a series of optimization techniques to improve the efficiency and robustness of RDMA-based communication. We implement FedRDMA atop the industrial federated learning framework and evaluate it on a real-world cross-silo FL scenario. The experimental results show that \sys can achieve up to 3.8$\times$ speedup in communication efficiency compared to traditional TCP/IP-based FL systems.

Lightweight Protection for Privacy in Offloaded Speech Understanding

Speech is a common input method for mobile embedded devices, but cloud-based speech recognition systems pose privacy risks. Disentanglement-based encoders, designed to safeguard user privacy by filtering sensitive information from speech signals, unfortunately require substantial memory and computational resources, which limits their use in less powerful devices. To overcome this, we introduce a novel system, XXX, optimized for such devices. XXX is built on the insight that speech understanding primarily relies on understanding the entire utterance's long-term dependencies, while privacy concerns are often linked to short-term details. Therefore, XXX focuses on selectively masking these short-term elements, preserving the quality of long-term speech understanding. The core of XXX is an innovative differential mask generator, grounded in interpretable learning, which fine-tunes the masking process. We tested XXX on the STM32H7 microcontroller, assessing its performance in various potential attack scenarios. The results show that XXX maintains speech understanding accuracy and privacy at levels comparable to existing encoders, but with a significant improvement in efficiency, achieving up to 53.3$\times$ faster processing and a 134.1$\times$ smaller memory footprint.

A Survey of Resource-efficient LLM and Multimodal Foundation Models

Large foundation models, including large language models (LLMs), vision transformers (ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine learning lifecycle, from training to deployment. However, the substantial advancements in versatility and performance these models offer come at a significant cost in terms of hardware resources. To support the growth of these large models in a scalable and environmentally sustainable way, there has been a considerable focus on developing resource-efficient strategies. This survey delves into the critical importance of such research, examining both algorithmic and systemic aspects. It offers a comprehensive analysis and valuable insights gleaned from existing literature, encompassing a broad array of topics from cutting-edge model architectures and training/serving algorithms to practical system designs and implementations. The goal of this survey is to provide an overarching understanding of how current approaches are tackling the resource challenges posed by large foundation models and to potentially inspire future breakthroughs in this field.

Rethinking Mobile AI Ecosystem in the LLM Era

In today's landscape, smartphones have evolved into hubs for hosting a multitude of deep learning models aimed at local execution. A key realization driving this work is the notable fragmentation among these models, characterized by varied architectures, operators, and implementations. This fragmentation imposes a significant burden on the comprehensive optimization of hardware, system settings, and algorithms. Buoyed by the recent strides in large foundation models, this work introduces a pioneering paradigm for mobile AI: a collaborative management approach between the mobile OS and hardware, overseeing a foundational model capable of serving a broad spectrum of mobile AI tasks, if not all. This foundational model resides within the NPU and remains impervious to app or OS revisions, akin to firmware. Concurrently, each app contributes a concise, offline fine-tuned "adapter" tailored to distinct downstream tasks. From this concept emerges a concrete instantiation known as \sys. It amalgamates a curated selection of publicly available Large Language Models (LLMs) and facilitates dynamic data flow. This concept's viability is substantiated through the creation of an exhaustive benchmark encompassing 38 mobile AI tasks spanning 50 datasets, including domains such as Computer Vision (CV), Natural Language Processing (NLP), audio, sensing, and multimodal inputs. Spanning this benchmark, \sys unveils its impressive performance. It attains accuracy parity in 85\% of tasks, demonstrates improved scalability in terms of storage and memory, and offers satisfactory inference speed on Commercial Off-The-Shelf (COTS) mobile devices fortified with NPU support. This stands in stark contrast to task-specific models tailored for individual applications.

EdgeMoE: Fast On-Device Inference of MoE-based Large Language Models

Large Language Models (LLMs) such as GPTs and LLaMa have ushered in a revolution in machine intelligence, owing to their exceptional capabilities in a wide range of machine learning tasks. However, the transition of LLMs from data centers to edge devices presents a set of challenges and opportunities. While this shift can enhance privacy and availability, it is hampered by the enormous parameter sizes of these models, leading to impractical runtime costs. In light of these considerations, we introduce EdgeMoE, the first on-device inference engine tailored for mixture-of-expert (MoE) LLMs, a popular variant of sparse LLMs that exhibit nearly constant computational complexity as their parameter size scales. EdgeMoE achieves both memory and computational efficiency by strategically partitioning the model across the storage hierarchy. Specifically, non-expert weights are stored in the device's memory, while expert weights are kept in external storage and are fetched into memory only when they are activated. This design is underpinned by a crucial insight that expert weights, though voluminous, are infrequently accessed due to sparse activation patterns. To further mitigate the overhead associated with expert I/O swapping, EdgeMoE incorporates two innovative techniques: (1) Expert-wise bitwidth adaptation: This method reduces the size of expert weights with an acceptable level of accuracy loss. (2) Expert management: It predicts the experts that will be activated in advance and preloads them into the compute-I/O pipeline, thus further optimizing the process. In empirical evaluations conducted on well-established MoE LLMs and various edge devices, EdgeMoE demonstrates substantial memory savings and performance improvements when compared to competitive baseline solutions.

Federated Fine-tuning of Billion-Sized Language Models across Mobile Devices

Large Language Models (LLMs) are transforming the landscape of mobile intelligence. Federated Learning (FL), a method to preserve user data privacy, is often employed in fine-tuning LLMs to downstream mobile tasks, an approach known as FedLLM. Though recent efforts have addressed the network issue induced by the vast model size, they have not practically mitigated vital challenges concerning integration with mobile devices, such as significant memory consumption and sluggish model convergence. In response to these challenges, this work introduces FwdLLM, an innovative FL protocol designed to enhance the FedLLM efficiency. The key idea of FwdLLM to employ backpropagation (BP)-free training methods, requiring devices only to execute ``perturbed inferences''. Consequently, FwdLLM delivers way better memory efficiency and time efficiency (expedited by mobile NPUs and an expanded array of participant devices). FwdLLM centers around three key designs: (1) it combines BP-free training with parameter-efficient training methods, an essential way to scale the approach to the LLM era; (2) it systematically and adaptively allocates computational loads across devices, striking a careful balance between convergence speed and accuracy; (3) it discriminatively samples perturbed predictions that are more valuable to model convergence. Comprehensive experiments with five LLMs and three NLP tasks illustrate FwdLLM's significant advantages over conventional methods, including up to three orders of magnitude faster convergence and a 14.6x reduction in memory footprint. Uniquely, FwdLLM paves the way for federated learning of billion-parameter LLMs such as LLaMA on COTS mobile devices -- a feat previously unattained.