SPFresh: Incremental In-Place Update for Billion-Scale Vector Search
Approximate Nearest Neighbor Search (ANNS) is now widely used in various applications including information retrieval, question answering, and recommendation. As the amount of vector data grows continuously, it becomes important to support updates to vector index, the enabling technique that allows for efficient and accurate ANNS on vectors.
Because of the curse of high dimensionality, it is often costly to identify the right neighbors of a single new vector, a necessary process for index update. To amortize update costs, existing systems maintain a secondary index to accumulate updates, which are merged by the main index by global rebuilding the entire index periodically. However, this approach has high fluctuations of search latency and accuracy, not even to mention that it requires substantial resources and is extremely time-consuming for rebuilds.
We introduce SPFresh, a system that supports in-place vector updates. At the heart of SPFresh is LIRE, a lightweight incremental rebalancing protocol to split vector partitions and reassign vectors in the nearby partitions to adapt to data distribution shift. LIRE achieves low-overhead vector updates by only reassigning vectors at the boundary between partitions, where in a high-quality vector index the amount of such vectors are deemed small. With LIRE, SPFresh provides superior query latency and accuracy to solutions based on global rebuild, with only 1% of DRAM and less than 10% cores needed at the peak compared to the state-of-the-art, in a billion scale disk-based vector index with a 1% of daily vector update rate.
In this paper, we present Brainstorm, a deep learning framework for optimizing dynamic NNs, which bridges the gap by unifying how dynamism should be expressed. Brainstorm proposes (1) Cell, the key data abstraction that lets model developers express the data granularity where dynamism exists, and (2) Router, a unified interface to let model developers express how Cells should be dynamically dispatched. Brainstorm handles efficient execution of routing actions. This design allows Brainstorm to collect profiles of fine-grained dataflow at the correct granularity. The traceability further opens up a new space of dynamic optimization for dynamic NNs to specialize their execution to the runtime dynamism distribution. Extensive evaluations show Brainstorm brings up to 11.7× speedup (3.29× on average) or leads to 42% less memory consumption for popular dynamic neural networks with the proposed dynamic optimizations.
PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation
Dynamic sparsity, where the sparsity patterns are unknown until runtime, poses a significant challenge to deep learning. The state-of-the-art sparsity-aware deep learning solutions are restricted to pre-defined, static sparsity patterns due to significant overheads associated with preprocessing. Efficient execution of dynamic sparse computation often faces the misalignment between the GPU-friendly tile configuration for efficient execution and the sparsity-aware tile shape that minimizes coverage wastes (non-zero values in tensor).
In this paper, we propose PIT, a deep-learning compiler for dynamic sparsity. PIT proposes a novel tiling mechanism that leverages Permutation Invariant Transformation (PIT), a mathematically proven property, to transform multiple sparsely located micro-tiles into a GPU-efficient dense tile without changing the computation results, thus achieving both high GPU utilization and low coverage waste. Given a model, PIT first finds feasible PIT rules for all its operators and generates efficient GPU kernels accordingly. At runtime, with the SRead and SWrite primitives, PIT rules can be executed extremely fast to support dynamic sparsity in an online manner. Extensive evaluation on diverse models shows that PIT can accelerate dynamic sparsity computation by up to 5.9x over state-of-the-art compilers.
End-to-End Word-Level Pronunciation Assessment with MASK Pre-training
Pronunciation assessment is a major challenge in the computer-aided pronunciation training system, especially at the word (phoneme)-level. To obtain word (phoneme)-level scores, current methods usually rely on aligning components to obtain acoustic features of each word (phoneme), which limits the performance of assessment to the accuracy of alignments. Therefore, to address this problem, we propose a simple yet effective method, namely \underline{M}asked pre-training for \underline{P}ronunciation \underline{A}ssessment (MPA). Specifically, by incorporating a mask-predict strategy, our MPA supports end-to-end training without leveraging any aligning components and can solve misalignment issues to a large extent during prediction. Furthermore, we design two evaluation strategies to enable our model to conduct assessments in both unsupervised and supervised settings. Experimental results on SpeechOcean762 dataset demonstrate that MPA could achieve better performance than previous methods, without any explicit alignment. In spite of this, MPA still has some limitations, such as requiring more inference time and reference text. They expect to be addressed in future work.
Accurate and Structured Pruning for Efficient Automatic Speech Recognition
Automatic Speech Recognition (ASR) has seen remarkable advancements with deep neural networks, such as Transformer and Conformer. However, these models typically have large model sizes and high inference costs, posing a challenge to deploy on resource-limited devices. In this paper, we propose a novel compression strategy that leverages structured pruning and knowledge distillation to reduce the model size and inference cost of the Conformer model while preserving high recognition performance. Our approach utilizes a set of binary masks to indicate whether to retain or prune each Conformer module, and employs L0 regularization to learn the optimal mask values. To further enhance pruning performance, we use a layerwise distillation strategy to transfer knowledge from unpruned to pruned models. Our method outperforms all pruning baselines on the widely used LibriSpeech benchmark, achieving a 50% reduction in model size and a 28% reduction in inference cost with minimal performance loss.
DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory
Controllable video generation has gained significant attention in recent years. However, two main limitations persist: Firstly, most existing works focus on either text, image, or trajectory-based control, leading to an inability to achieve fine-grained control in videos. Secondly, trajectory control research is still in its early stages, with most experiments being conducted on simple datasets like Human3.6M. This constraint limits the models’ capability to process open-domain images and effectively handle complex curved trajectories. In this paper, we propose DragNUWA, an open-domain diffusion-based video generation model. To tackle the issue of insufficient control granularity in existing works, we simultaneously introduce text, image, and trajectory information to provide fine-grained control over video content from semantic, spatial, and temporal perspectives. To resolve the problem of limited open-domain trajectory control in current research, we propose trajectory modeling with three aspects: a Trajectory Sampler (TS) to enable open-domain control of arbitrary trajectories, a Multiscale Fusion (MF) to control trajectories in different granularities, and an Adaptive Training (AT) strategy to generate consistent videos following trajectories. Our experiments validate the effectiveness of DragNUWA, demonstrating its superior performance in fine-grained control in video generation.
Generative Retrieval for Conversational Question Answering
Effective passage retrieval is crucial for conversation question answering (QA) but challenging due to the ambiguity of questions. Current methods rely on the dual-encoder architecture to embed contextualized vectors of questions in conversations. However, this architecture is limited in the embedding bottleneck and the dot-product operation. To alleviate these limitations, we propose generative retrieval for conversational QA (GCoQA). GCoQA assigns distinctive identifiers for passages and retrieves passages by generating their identifiers token-by-token via the encoder–decoder architecture. In this generative way, GCoQA eliminates the need for a vector-style index and could attend to crucial tokens of the conversation context at every decoding step. We conduct experiments on three public datasets over a corpus containing about twenty million passages. The results show GCoQA achieves relative improvements of +13.6% in passage retrieval and +42.9% in document retrieval. GCoQA is also efficient in terms of memory usage and inference speed, which only consumes 1/10 of the memory and takes in less than 33% of the time. The code and data are released at https://github.com/liyongqi67/GCoQA
In this paper, we propose PIT, a deep-learning compiler for dynamic sparsity. PIT proposes a novel tiling mechanism that leverages Permutation Invariant Transformation (PIT), a mathematically proven property, to transform multiple sparsely located micro-tiles into a GPU-efficient dense tile without changing the computation results, thus achieving both high GPU utilization and low coverage waste. Given a model, PIT first finds feasible PIT rules for all its operators and generates efficient GPU kernels accordingly. At runtime, with the SRead and SWrite primitives, PIT rules can be executed extremely fast to support dynamic sparsity in an online manner. Extensive evaluation on diverse models shows that PIT can accelerate dynamic sparsity computation by up to 5.9x over state-of-the-art compilers.