Search Results for author:
Found 20 papers, 8 papers with code
CATS: Mitigating Correlation Shift for Multivariate Time Series Classification
Given the prevalence of multivariate time series (MTS) data across various domains, the UDA task for MTS classification has emerged as a critical challenge.
ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration
Mixture-of-Experts (MoE) Transformer, the backbone architecture of multiple phenomenal language models, leverages sparsity by activating only a fraction of model parameters for each input token.
Exploring the Performance Improvement of Tensor Processing Engines through Transformation in the Bit-weight Dimension of MACs
Based on this notation and its transformations, we propose four optimization techniques that improve timing, area, and power consumption.
Joint Optimal Transport and Embedding for Network Alignment
For one thing (OT for embedding), through a simple yet effective transformation, the noise-reduced OT mapping serves as an adaptive sampling strategy directly modeling all cross-network node pairs for robust embedding learning. For another (embedding for OT), on top of the learned embeddings, the OT cost can be gradually trained in an end-to-end fashion, which further enhances the alignment quality.
Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
Reinforcement learning from human feedback (RLHF) has demonstrated remarkable effectiveness in aligning large language models (LLMs) with human preferences.
External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation
Second, large-volume data arrive in a streaming mode with data distributions dynamically shifting, as new users/ads join and existing users/ads leave the system.
Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs
Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding.
PyG-SSL: A Graph Self-Supervised Learning Toolkit
Graph Self-Supervised Learning (SSL) has emerged as a pivotal area of research in recent years.
THeGCN: Temporal Heterophilic Graph Convolutional Network
Furthermore, we highlight that the edge heterophily issue and the temporal heterophily issue often co-exist in event-based continuous graphs, giving rise to the temporal edge heterophily challenge.
A Collaborative Ensemble Framework for CTR Prediction
Recent advances in foundation models have established scaling laws that enable the development of larger models to achieve enhanced performance, motivating extensive research into large-scale recommendation models.
InterFormer: Towards Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction
A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction.
SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
Attention is the cornerstone of modern Large Language Models (LLMs).
AdaRC: Mitigating Graph Structure Shifts during Test-Time
However, existing TTA algorithms are primarily designed for attribute shifts in vision tasks, where samples are independent.
LUT Tensor Core: Lookup Table Enables Efficient Low-Bit LLM Inference Acceleration
Then, LUT Tensor Core proposes the hardware design featuring an elongated tiling shape design to enhance table reuse and a bit-serial design to support various precision combinations in mpGEMM.
AIM: Attributing, Interpreting, Mitigating Data Unfairness
Data collected in the real world often encapsulates historical discrimination against disadvantaged groups and individuals.
Discrete-state Continuous-time Diffusion for Graph Generation
Graph is a prevalent discrete data structure, whose generation has wide applications such as drug discovery and circuit design.
Allo: A Programming Model for Composable Accelerator Design
For the GPT2 model, the inference latency of the Allo generated accelerator is 1. 7x faster than the NVIDIA A100 GPU with 5. 4x higher energy efficiency, demonstrating the capability of Allo to handle large-scale designs.
Hierarchical Multi-Marginal Optimal Transport for Network Alignment
To depict high-order relationships across multiple networks, the FGW distance is generalized to the multi-marginal setting, based on which networks can be aligned jointly.
Ensuring User-side Fairness in Dynamic Recommender Systems
In the ever-evolving landscape of user-item interactions, continual adaptation to newly collected data is crucial for recommender systems to stay aligned with the latest user preferences.
Class-Imbalanced Graph Learning without Class Rebalancing
In this work, we approach the root cause of class-imbalance bias from an topological paradigm.
