Edge language models show bias over time, especially on resource-constrained devices.
problem Bias in edge language models on resource-constrained devices.
method Comparative analysis of text-based bias across edge, cloud, and desktop environments; optimized Llama-2 model on Raspberry Pi 4; feedback loop mechanism to correct bias.
result Llama-2 on Raspberry Pi 4 shows 43.23% and 21.89% more bias over time compared to cloud and desktop models.
Local SGD outperforms conventional methods in LLM training.
problem Training large language models on distributed devices.
method Local SGD algorithm applied to distributed training.
result Local SGD achieves competitive results in LLM training.
SLIP secures LLMs on edge devices by splitting computation and protecting sensitive parts.
problem Protecting LLMs on edge devices from theft and unauthorized use.
method SLIP uses matrix decomposition to split model computation between secure and vulnerable resources, ensuring zero accuracy degradation and minimal latency.
result SLIP is the first practical, secure hybrid protocol for protecting LLMs on edge devices.
The paper studies how search and distillation improve reasoning in large language models.
problem Improving reasoning capabilities of large language models.
method Viewing chain-of-thought generation as a metastable Markov process, proving benefits of search and distillation.
result Search protocol rewards sparse edges, reducing the expected number of steps to reach different clusters.
Recently, pre-trained language representation flourishes as the mainstay of the natural language understanding community, e.g., BERT. These pre-trained language representations can create state-of-the-art results on a wide range of downstream tasks. Along with continuous significant performance improvement, the size an…
This paper enhances language models with knowledge awareness.
problem Understanding how much knowledge pretrained language models grasp.
method Inserting explicit knowledge layers into pretraining without changing transformer architecture.
result Significantly more knowledge packed into transformer parameters.
We propose a new statistical model suitable for machine learning of systems with long distance correlations such as natural languages. The model is based on directed acyclic graph decorated by multi-linear tensor maps in the vertices and vector spaces in the edges, called tensor network. Such tensor networks have been …
Graph data augmentation improves GNN performance in node classification.
problem Improving generalizability of graph neural networks (GNNs) in semi-supervised node classification.
method Introduces GAug framework for graph data augmentation using neural edge predictors.
result GAug framework improves GNN-based node classification performance across various architectures and datasets.
Paper presents a lightweight, unobtrusive method to protect edge device data privacy.
problem Protecting inference data privacy in IoT edge devices with limited compute power.
method A lightweight neural network at edge devices to obfuscate inference data without indicating obfuscation.
result Effectively protects inference data confidentiality while preserving backend accuracy.
We propose a method for non-projective dependency parsing by incrementally predicting a set of edges. Since the edges do not have a pre-specified order, we propose a set-based learning method. Our method blends graph, transition, and easy-first parsing, including a prior state of the parser as a special case. The propo…
KodeXv0.1 improves financial question answering over GPT-4.
problem Lack of specialized financial language models.
method Custom training on financial documents, RAG-aware 4bit LoRA tuning.
result KodeX-8Bv0.1 outperforms GPT-4 by up to 9.24% in financial tasks.
CALDERA compresses large language models by approximating weight matrices with low-rank, low-precision factors.
problem The large sizes of Large Language Models (LLMs) hinder deployment on edge devices.
method CALDERA approximates weight matrices W as Q+LR, where L and R are low-rank factors quantized to low precision. result CALDERA achieves better zero-shot performance than existing techniques, especially with low bit precision.
This paper tackles graph translation challenges by predicting both node and edge attributes simultaneously.
problem Challenges in predicting both node and edge attributes in graph translation, especially in interactive, iterative, and asynchronous processes.
method Developed a novel framework integrating both node and edge translations seamlessly, using spectral graph regularization to maintain consistency.
result Demonstrated the effectiveness of the proposed method on both synthetic and real-world application data.
We study the problem of finding the minimal (maximal) genus for a surface where a given four-valent graph with fixed opposite edge structure can be embedded into. We find several partial relations and give new reformulations in combinatorial and knot theoretic languages.
Improved financial network predictability using LLM for edge filtering.
problem Spurious edges in financial networks from textual similarity.
method Two-stage framework: sparse candidate graph + LLM edge classification.
result LLM-based edge filtering improves Sharpe ratio and reduces drawdown.
StableLM 2 1.6B is a new language model series with detailed evaluations and performance metrics.
problem Improving language models with smaller sizes and better performance.
method Detailed data and training procedure for StableLM 2 1.6B, including zero- and few-shot benchmarks and multilingual evaluations.
result StableLM 2 1.6B is the state-of-the-art open model under 2B parameters.
SWIFT improves time series forecasting on edge devices with wavelet decomposition.
problem Efficient time series forecasting on resource-constrained devices.
method Wavelet decomposition, cross-band fusion, and shared linear mapping.
result SWIFT achieves state-of-the-art performance on multiple datasets.
PriceSeer benchmarks LLMs in real-time stock prediction.
problem Evaluating LLMs' stock prediction accuracy and robustness.
method Real-time benchmark with 110 U.S. stocks, internal and external information expansion.
result LLMs perform suboptimally in long-term predictions due to fake news and specific industries.
GraphToken encodes structured data for LLMs, improving graph reasoning tasks.
problem Efficiently encoding structured data for large language models.
method GraphToken learns an encoding function to extend prompts with explicit structured information.
result Significant improvements across node, edge, and graph-level tasks on the GraphQA benchmark.
Efficient algorithm for matching graphs with community structure.
problem Graph matching between correlated stochastic block models with constant correlation.
method Partition trees rooted from each vertex, comparing edge statistics to different communities.
result First low-order polynomial-time algorithm achieving exact matching with high probability in dense graphs.
Graph Weighted Models (GWMs) have recently been proposed as a natural generalization of weighted automata over strings and trees to arbitrary families of labeled graphs (and hypergraphs). A GWM generically associates a labeled graph with a tensor network and computes a value by successive contractions directed by its e…
Compact Recurrent Transformer (CRT) improves Transformer efficiency for long sequences.
problem Efficiently scaling Transformer architecture to long sequences with limited compute resources.
method Combines shallow Transformer models with recurrent neural networks and persistent memory.
result CRT achieves comparable or superior performance to full-length Transformers with shorter segments and reduced FLOPs.
Structure learning in random fields has attracted considerable attention due to its difficulty and importance in areas such as remote sensing, computational biology, natural language processing, protein networks, and social network analysis. We consider the problem of estimating the probabilistic graph structure associ…
AutoGraph uses transformers to efficiently generate graphs as sequences.
problem Efficiently generating large, sparse graphs without expensive node features.
method Flattening graphs into sequences and using decoder-only transformers.
result AutoGraph achieves state-of-the-art performance on synthetic and molecular benchmarks.
The techniques of deep learning have become the state of the art methodology for executing complicated tasks from various domains of computer vision, natural language processing, and several other areas. Due to its rapid development and promising benchmarks in those fields, researchers started experimenting with this t…
This paper explores how NLP enhances insurance data analysis.
problem Traditional insurance data limitations and need for alternative data.
method Application of NLP techniques to transform and analyze unstructured text data.
result NLP techniques improve insurance data analysis and risk assessment.
AutoShrink optimizes neural architectures by shrinking cell structures.
problem Resource constraints in deploying DNNs on mobile devices.
method Topology-aware node-based Neural Architecture Search (NAS).
result AutoShrink achieves up to 48% parameter reduction and 34% MACs savings.
We introduce a scalable measure of curvature for analyzing training dynamics of large language models.
problem Analyzing the training dynamics of large language models due to high computational cost of measuring Hessian sharpness.
method We introduce critical sharpness and relative critical sharpness as computationally efficient measures capturing Hessian sharpness phenomena.
result We provide the first demonstration of sharpness phenomena at scale up to 7B parameters.
The study examines spectral dynamics in deep neural networks, predicting how outliers evolve during training.
problem Understanding spectral evolution in deep neural networks during training.
method Developed a two-level dynamical mean-field theory (DMFT) to track spectral dynamics.
result The theory predicts how outliers evolve with training time, width, output scale, and initialization variance.
New method compresses LSTM networks using MPS tensor trains.
problem Challenges in maintaining performance of compressed RNNs.
method Use of MPS tensor trains for LSTM network compression.
result MPS tensor trains outperform MPOs in storage and inference time.
The Perona-Malik model has been very successful at restoring images from noisy input. In this paper, we reinterpret the Perona-Malik model in the language of Gaussian scale mixtures and derive some extensions of the model. Specifically, we show that the expectation-maximization (EM) algorithm applied to Gaussian scale …
Paper detects anomalous edges in social networks using edge exchangeability.
problem Detecting anomalous edges in directed social networks.
method Exploits edge exchangeability and uses conformal prediction theory.
result Proposed anomaly detector has a guaranteed upper bound for false positives.
Recurrent neural networks (RNNs) have recently achieved remarkable successes in a number of applications. However, the huge sizes and computational burden of these models make it difficult for their deployment on edge devices. A practically effective approach is to reduce the overall storage and computation costs of RN…
Path queries on a knowledge graph can be used to answer compositional questions such as "What languages are spoken by people living in Lisbon?". However, knowledge graphs often have missing facts (edges) which disrupts path queries. Recent models for knowledge base completion impute missing facts by embedding knowledge…
We extend the edge version of the classical Menger's Theorem for undirected graphs to n-dimensional simplicial complexes with chains over the field F2. The classical Menger's Theorem states that two different vertices in an undirected graph can be connected by k pairwise edge-disjoint paths if, and only…
Neural embeddings have been used with great success in Natural Language Processing (NLP). They provide compact representations that encapsulate word similarity and attain state-of-the-art performance in a range of linguistic tasks. The success of neural embeddings has prompted significant amounts of research into appli…
New method for embedding large networks without attributes, achieving state-of-the-art performance.
problem Learning embeddings from large-scale networks without domain-dependent attributes.
method Use predefined local encodings based on node degree frequencies at different distances.
result Inductive network embeddings generalize well across unseen or distant regions in the network.
A {\it blink} is a plane graph with its edges being red or green. A {\it 3D-space} or, simply, a {\it space} is a connected, closed and oriented 3-manifold. In this work we explore in details, for the first time, the fact that every blink induces a space and any space is induced by some blink (actually infinitely many …
Machine learning models that take computer program source code as input typically use Natural Language Processing (NLP) techniques. However, a major challenge is that code is written using an open, rapidly changing vocabulary due to, e.g., the coinage of new variable and method names. Reasoning over such a vocabulary i…
Recurrent neural networks (RNNs) achieve cutting-edge performance on a variety of problems. However, due to their high computational and memory demands, deploying RNNs on resource constrained mobile devices is a challenging task. To guarantee minimum accuracy loss with higher compression rate and driven by the mobile r…
Textual network embedding leverages rich text information associated with the network to learn low-dimensional vectorial representations of vertices. Rather than using typical natural language processing (NLP) approaches, recent research exploits the relationship of texts on the same edge to graphically embed text. How…
New GPs model edge functions on complex networks, capturing divergence and curl.
problem Modeling flow data on networks with independent learning of Hodge components.
method Developed Hodge-compositional edge GPs using Hodge decomposition.
result Hodge-compositional edge GPs can represent any edge function and capture flow relevance.
Survey on LLMs for time series analytics across various domains.
problem Cross-modality gap between LLMs and time series data.
method Taxonomy of approaches, cross-modality strategies, and experiments on multimodal datasets.
result Effective combinations of textual data and cross-modality strategies enhance time series analytics.
Transformer adapts to graphs with adaptive attention and auto-regressive decoding.
problem Transformers struggle with graph data due to non-sequential nature.
method Proposes GRAT, a Transformer variant with adaptive attention and auto-regressive decoding.
result GRAT achieves state-of-the-art performance on molecule property predictions and generation tasks.
SparseIDS uses RL to significantly reduce packet inspection in IDSs.
problem Efficiently inspecting large volumes of network packets for security threats.
method SparseIDS employs RL to learn optimal packet sampling strategies.
result SparseIDS reduces packet inspection by more than 75% while maintaining high accuracy.
On-device federated learning updates edge models by exchanging trained results.
problem Limited training data at edge devices due to model drift.
method OS-ELM for sequential training and autoencoder for anomaly detection, combined with federated learning.
result The proposed approach produces a merged model as accurately as traditional methods with lower costs.
Method certifies edge predictions with cloud-level reliability.
problem Ensuring reliability of edge intelligence models.
method Conformal alignment-based cascading mechanism.
result Certifies conditional coverage with user control over risk level.
Pólya's theorem extended to meromorphic functions on Riemann surfaces.
problem Distribution of zeros of iterated derivatives of meromorphic functions.
method Recasting local arguments into translation surfaces and using flat metrics.
result Asymptotic distribution of zeros on compact Riemann surfaces.