Multi-Token Joint Speculative Decoding for Accelerating Large Language Model Inference

Transformer-based Large language models (LLMs) have demonstrated their power in various tasks, but their inference incurs significant time and energy costs. To accelerate LLM inference, speculative decoding uses a smaller model to propose one sequence of tokens, which are subsequently validated in batch by the target large model. Compared with autoregressive decoding, speculative decoding generates the same number of tokens with fewer runs of the large model, hence accelerating the overall inference by $1$-$2\times$. However, greedy decoding is not the optimal decoding algorithm in terms of output perplexity, which is a direct measurement of the effectiveness of a decoding algorithm. An algorithm that has better output perplexity and even better efficiency than speculative decoding can be more useful in practice. To achieve this seemingly contradictory goal, we first introduce multi-token joint greedy decoding (MJGD), which greedily generates multiple tokens at each step based on their joint perplexity. We show that it leads to better perplexity for the whole output. But the computation cost of MJGD is infeasible in practice. So we further propose multi-token joint speculative decoding (MJSD), which approximates and accelerates the MJGD from two aspects: it approximates the joint distribution of the large model with that of a small model, and uses a verification step to guarantee the accuracy of approximation; then it uses beam decoding to accelerate the sequence generation from the joint distribution. Compared with vanilla speculative decoding, MJSD has two advantages: (1) it is an approximation of MJGD, thus achieving better output perplexity; (2) verification with joint likelihood allows it to accept the longest prefix sub-sequence of the draft tokens with valid perplexity, leading to better efficiency...

SparseCL: Sparse Contrastive Learning for Contradiction Retrieval

Contradiction retrieval refers to identifying and extracting documents that explicitly disagree with or refute the content of a query, which is important to many downstream applications like fact checking and data cleaning. To retrieve contradiction argument to the query from large document corpora, existing methods such as similarity search and crossencoder models exhibit significant limitations. The former struggles to capture the essence of contradiction due to its inherent nature of favoring similarity, while the latter suffers from computational inefficiency, especially when the size of corpora is large. To address these challenges, we introduce a novel approach: SparseCL that leverages specially trained sentence embeddings designed to preserve subtle, contradictory nuances between sentences. Our method utilizes a combined metric of cosine similarity and a sparsity function to efficiently identify and retrieve documents that contradict a given query. This approach dramatically enhances the speed of contradiction detection by reducing the need for exhaustive document comparisons to simple vector calculations. We validate our model using the Arguana dataset, a benchmark dataset specifically geared towards contradiction retrieval, as well as synthetic contradictions generated from the MSMARCO and HotpotQA datasets using GPT-4. Our experiments demonstrate the efficacy of our approach not only in contradiction retrieval with more than 30% accuracy improvements on MSMARCO and HotpotQA across different model architectures but also in applications such as cleaning corrupted corpora to restore high-quality QA retrieval. This paper outlines a promising direction for improving the accuracy and efficiency of contradiction retrieval in large-scale text corpora.

Hierarchical Compression of Text-Rich Graphs via Large Language Models

Text-rich graphs, prevalent in data mining contexts like e-commerce and academic graphs, consist of nodes with textual features linked by various relations. Traditional graph machine learning models, such as Graph Neural Networks (GNNs), excel in encoding the graph structural information, but have limited capability in handling rich text on graph nodes. Large Language Models (LLMs), noted for their superior text understanding abilities, offer a solution for processing the text in graphs but face integration challenges due to their limitation for encoding graph structures and their computational complexities when dealing with extensive text in large neighborhoods of interconnected nodes. This paper introduces ``Hierarchical Compression'' (HiCom), a novel method to align the capabilities of LLMs with the structure of text-rich graphs. HiCom processes text in a node's neighborhood in a structured manner by organizing the extensive textual information into a more manageable hierarchy and compressing node text step by step. Therefore, HiCom not only preserves the contextual richness of the text but also addresses the computational challenges of LLMs, which presents an advancement in integrating the text processing power of LLMs with the structural complexities of text-rich graphs. Empirical results show that HiCom can outperform both GNNs and LLM backbones for node classification on e-commerce and citation graphs. HiCom is especially effective for nodes from a dense region in a graph, where it achieves a 3.48% average performance improvement on five datasets while being more efficient than LLM backbones.

Automated Molecular Concept Generation and Labeling with Large Language Models

Artificial intelligence (AI) is significantly transforming scientific research. Explainable AI methods, such as concept-based models (CMs), are promising for driving new scientific discoveries because they make predictions based on meaningful concepts and offer insights into the prediction process. In molecular science, however, explainable CMs are not as common compared to black-box models like Graph Neural Networks (GNNs), primarily due to their requirement for predefined concepts and manual label for each instance, which demand domain knowledge and can be labor-intensive. This paper introduces a novel framework for Automated Molecular Concept (AutoMolCo) generation and labeling. AutoMolCo leverages the knowledge in Large Language Models (LLMs) to automatically generate predictive molecular concepts and label them for each molecule. Such procedures are repeated through iterative interactions with LLMs to refine concepts, enabling simple linear models on the refined concepts to outperform GNNs and LLM in-context learning on several benchmarks. The whole AutoMolCo framework is automated without any human knowledge inputs in either concept generation, labeling, or refinement, thereby surpassing the limitations of extant CMs while maintaining their explainability and allowing easy intervention. Through systematic experiments on MoleculeNet and High-Throughput Experimentation (HTE) datasets, we demonstrate that the AutoMolCo-induced explainable CMs are beneficial and promising for molecular science research.

Cross-Modality Program Representation Learning for Electronic Design Automation with High-Level Synthesis

In recent years, domain-specific accelerators (DSAs) have gained popularity for applications such as deep learning and autonomous driving. To facilitate DSA designs, programmers use high-level synthesis (HLS) to compile a high-level description written in C/C++ into a design with low-level hardware description languages that eventually synthesize DSAs on circuits. However, creating a high-quality HLS design still demands significant domain knowledge, particularly in microarchitecture decisions expressed as \textit{pragmas}. Thus, it is desirable to automate such decisions with the help of machine learning for predicting the quality of HLS designs, requiring a deeper understanding of the program that consists of original code and pragmas. Naturally, these programs can be considered as sequence data. In addition, these programs can be compiled and converted into a control data flow graph (CDFG). But existing works either fail to leverage both modalities or combine the two in shallow or coarse ways. We propose ProgSG, a model that allows interaction between the source code sequence modality and the graph modality in a deep and fine-grained way. To alleviate the scarcity of labeled designs, a pre-training method is proposed based on a suite of compiler's data flow analysis tasks. Experimental results show that ProgSG reduces the RMSE of design performance predictions by up to $22\%$, and identifies designs with an average of $1.10\times$ and $1.26\times$ (up to $8.17\times$ and $13.31\times$) performance improvement in design space exploration (DSE) task compared to HARP and AutoDSE, respectively.

VideoPhy: Evaluating Physical Commonsense for Video Generation

Recent advances in internet-scale video data pretraining have led to the development of text-to-video generative models that can create high-quality videos across a broad range of visual concepts and styles. Due to their ability to synthesize realistic motions and render complex objects, these generative models have the potential to become general-purpose simulators of the physical world. However, it is unclear how far we are from this goal with the existing text-to-video generative models. To this end, we present VideoPhy, a benchmark designed to assess whether the generated videos follow physical commonsense for real-world activities (e.g. marbles will roll down when placed on a slanted surface). Specifically, we curate a list of 688 captions that involve interactions between various material types in the physical world (e.g., solid-solid, solid-fluid, fluid-fluid). We then generate videos conditioned on these captions from diverse state-of-the-art text-to-video generative models, including open models (e.g., VideoCrafter2) and closed models (e.g., Lumiere from Google, Pika). Further, our human evaluation reveals that the existing models severely lack the ability to generate videos adhering to the given text prompts, while also lack physical commonsense. Specifically, the best performing model, Pika, generates videos that adhere to the caption and physical laws for only 19.7% of the instances. VideoPhy thus highlights that the video generative models are far from accurately simulating the physical world. Finally, we also supplement the dataset with an auto-evaluator, VideoCon-Physics, to assess semantic adherence and physical commonsense at scale.

Mixture of In-Context Prompters for Tabular PFNs

Recent benchmarks found In-Context Learning (ICL) outperforms both deep learning and tree-based algorithms on small tabular datasets. However, on larger datasets, ICL for tabular learning cannot run without severely compromising performance, due to its quadratic space and time complexity w.r.t. dataset size. We propose MIXTUREPFN, which both extends nearest-neighbor sampling to the state-of-the-art ICL for tabular learning model and uses bootstrapping to finetune said model on the inference-time dataset. MIXTUREPFN is the Condorcet winner across 36 diverse tabular datasets against 19 strong deep learning and tree-based baselines, achieving the highest mean rank among Top-10 aforementioned algorithms with statistical significance.

HMT: Hierarchical Memory Transformer for Long Context Language Processing

Transformer-based large language models (LLM) have been widely used in language processing applications. However, most of them restrict the context window that permits the model to attend to every token in the inputs. Previous works in recurrent models can memorize past tokens to enable unlimited context and maintain effectiveness. However, they have "flat" memory architectures, which have limitations in selecting and filtering information. Since humans are good at learning and self-adjustment, we speculate that imitating brain memory hierarchy is beneficial for model memorization. We propose the Hierarchical Memory Transformer (HMT), a novel framework that enables and improves models' long-context processing ability by imitating human memorization behavior. Leveraging memory-augmented segment-level recurrence, we organize the memory hierarchy by preserving tokens from early input token segments, passing memory embeddings along the sequence, and recalling relevant information from history. Evaluating general language modeling (Wikitext-103, PG-19) and question-answering tasks (PubMedQA), we show that HMT steadily improves the long-context processing ability of context-constrained and long-context models. With an additional 0.5% - 2% of parameters, HMT can easily plug in and augment future LLMs to handle long context effectively. Our code is open-sourced on Github: https://github.com/OswaldHe/HMT-pytorch.

BrainODE: Dynamic Brain Signal Analysis via Graph-Aided Neural Ordinary Differential Equations

Brain network analysis is vital for understanding the neural interactions regarding brain structures and functions, and identifying potential biomarkers for clinical phenotypes. However, widely used brain signals such as Blood Oxygen Level Dependent (BOLD) time series generated from functional Magnetic Resonance Imaging (fMRI) often manifest three challenges: (1) missing values, (2) irregular samples, and (3) sampling misalignment, due to instrumental limitations, impacting downstream brain network analysis and clinical outcome predictions. In this work, we propose a novel model called BrainODE to achieve continuous modeling of dynamic brain signals using Ordinary Differential Equations (ODE). By learning latent initial values and neural ODE functions from irregular time series, BrainODE effectively reconstructs brain signals at any time point, mitigating the aforementioned three data challenges of brain signals altogether. Comprehensive experimental results on real-world neuroimaging datasets demonstrate the superior performance of BrainODE and its capability of addressing the three data challenges.

Parameter-Efficient Tuning Large Language Models for Graph Representation Learning

Text-rich graphs, which exhibit rich textual information on nodes and edges, are prevalent across a wide range of real-world business applications. Large Language Models (LLMs) have demonstrated remarkable abilities in understanding text, which also introduced the potential for more expressive modeling in text-rich graphs. Despite these capabilities, efficiently applying LLMs to representation learning on graphs presents significant challenges. Recently, parameter-efficient fine-tuning methods for LLMs have enabled efficient new task generalization with minimal time and memory consumption. Inspired by this, we introduce Graph-aware Parameter-Efficient Fine-Tuning - GPEFT, a novel approach for efficient graph representation learning with LLMs on text-rich graphs. Specifically, we utilize a graph neural network (GNN) to encode structural information from neighboring nodes into a graph prompt. This prompt is then inserted at the beginning of the text sequence. To improve the quality of graph prompts, we pre-trained the GNN to assist the frozen LLM in predicting the next token in the node text. Compared with existing joint GNN and LMs, our method directly generate the node embeddings from large language models with an affordable fine-tuning cost. We validate our approach through comprehensive experiments conducted on 8 different text-rich graphs, observing an average improvement of 2% in hit@1 and Mean Reciprocal Rank (MRR) in link prediction evaluations. Our results demonstrate the efficacy and efficiency of our model, showing that it can be smoothly integrated with various large language models, including OPT, LLaMA and Falcon.