arXiv subjects

Xiaohan Zhao

Publications and source records attributed to Xiaohan Zhao.

26 records · Page 2Linked to original sources

arXiv2023

More than Correlation: Do Large Language Models Learn Causal Representations of Space?

Recent work found high mutual information between the learned representations of large language models (LLMs) and the geospatial property of its input, hinting an emergent internal model of space. However, whether this internal space model has any causal effects on the LLMs' behaviors was not answered by that work, led to criticism of these findings as mere statistical correlation. Our study focused on uncovering the causality of the spatial representations in LLMs. In particular, we discovered the potential spatial representations in DeBERTa, GPT-Neo using representational similarity analysis and linear and non-linear probing. Our casual intervention experiments showed that the spatial representations influenced the model's performance on next word prediction and a downstream task that relies on geospatial information. Our experiments suggested that the LLMs learn and use an internal model of space in solving geospatial related tasks.

cs.CL↗

arXiv2022

Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning

To eliminate the requirement of fully-labeled data for supervised model training in traditional Federated Learning (FL), extensive attention has been paid to the application of Self-supervised Learning (SSL) approaches on FL to tackle the label scarcity problem. Previous works on Federated SSL generally fall into two categories: parameter-based model aggregation (i.e., FedAvg, applicable to homogeneous cases) or data-based feature sharing (i.e., knowledge distillation, applicable to heterogeneous cases) to achieve knowledge transfer among multiple unlabeled clients. Despite the progress, all of them inevitably rely on some assumptions, such as homogeneous models or the existence of an additional public dataset, which hinder the universality of the training frameworks for more general scenarios. Therefore, in this paper, we propose a novel and general method named Federated Self-supervised Learning with Feature-correlation based Aggregation (FedFoA) to tackle the above limitations in a communication-efficient and privacy-preserving manner. Our insight is to utilize feature correlation to align the feature mappings and calibrate the local model updates across clients during their local training process. More specifically, we design a factorization-based method to extract the cross-feature relation matrix from the local representations. Then, the relation matrix can be regarded as a carrier of semantic information to perform the aggregation phase. We prove that FedFoA is a model-agnostic training framework and can be easily compatible with state-of-the-art unsupervised FL methods. Extensive empirical experiments demonstrate that our proposed approach outperforms the state-of-the-art methods by a significant margin.

cs.LG↗

arXiv2022

GAGA: Deciphering Age-path of Generalized Self-paced Regularizer

Nowadays self-paced learning (SPL) is an important machine learning paradigm that mimics the cognitive process of humans and animals. The SPL regime involves a self-paced regularizer and a gradually increasing age parameter, which plays a key role in SPL but where to optimally terminate this process is still non-trivial to determine. A natural idea is to compute the solution path w.r.t. age parameter (i.e., age-path). However, current age-path algorithms are either limited to the simplest regularizer, or lack solid theoretical understanding as well as computational efficiency. To address this challenge, we propose a novel \underline{G}eneralized \underline{Ag}e-path \underline{A}lgorithm (GAGA) for SPL with various self-paced regularizers based on ordinary differential equations (ODEs) and sets control, which can learn the entire solution spectrum w.r.t. a range of age parameters. To the best of our knowledge, GAGA is the first exact path-following algorithm tackling the age-path for general self-paced regularizer. Finally the algorithmic steps of classic SVM and Lasso are described in detail. We demonstrate the performance of GAGA on real-world datasets, and find considerable speedup between our algorithm and competing baselines.

cs.LG↗

arXiv2020

EPIHC: Improving Enhancer-Promoter Interaction Prediction by using Hybrid features and Communicative learning

Enhancer-promoter interactions (EPIs) regulate the expression of specific genes in cells, and EPIs are important for understanding gene regulation, cell differentiation and disease mechanisms. EPI identification through the wet experiments is costly and time-consuming, and computational methods are in demand. In this paper, we propose a deep neural network-based method EPIHC based on sequence-derived features and genomic features for the EPI prediction. EPIHC extracts features from enhancer and promoter sequences respectively using convolutional neural networks (CNN), and then design a communicative learning module to captures the communicative information between enhancer and promoter sequences. EPIHC also take the genomic features of enhancers and promoters into account. At last, EPIHC combines sequence-derived features and genomic features to predict EPIs. The computational experiments show that EPIHC outperforms the existing state-of-the-art EPI prediction methods on the benchmark datasets and chromosome-split datasets, and the study reveal that the communicative learning module can bring explicit information about EPIs, which is ignore by CNN. Moreover, we consider two strategies to improve performances of EPIHC in the cross-cell line prediction, and experimental results show that EPIHC constructed on training cell lines exhibit improved performances for the other cell lines.

q-bio.GN↗

arXiv2015

Graph Watermarks

From network topologies to online social networks, many of today's most sensitive datasets are captured in large graphs. A significant challenge facing owners of these datasets is how to share sensitive graphs with collaborators and authorized users, e.g. network topologies with network equipment vendors or Facebook's social graphs with academic collaborators. Current tools can provide limited node or edge privacy, but require modifications to the graph that significantly reduce its utility. In this work, we propose a new alternative in the form of graph watermarks. Graph watermarks are small graphs tailor-made for a given graph dataset, a secure graph key, and a secure user key. To share a sensitive graph G with a collaborator C, the owner generates a watermark graph W using G, the graph key, and C's key as input, and embeds W into G to form G'. If G' is leaked by C,its owner can reliably determine if the watermark W generated for C does in fact reside inside G', thereby proving C is responsible for the leak. Graph watermarks serve both as a deterrent against data leakage and a method of recourse after a leak. We provide robust schemes for creating, embedding and extracting watermarks, and use analysis and experiments on large, real graphs to show that they are unique and difficult to forge. We study the robustness of graph watermarks against both single and powerful colluding attacker models, then propose and empirically evaluate mechanisms to dramatically improve resilience.

cs.CR↗

arXiv2012

Serf and Turf: Crowdturfing for Fun and Profit

Popular Internet services in recent years have shown that remarkable things can be achieved by harnessing the power of the masses using crowd-sourcing systems. However, crowd-sourcing systems can also pose a real challenge to existing security mechanisms deployed to protect Internet services. Many of these techniques make the assumption that malicious activity is generated automatically by machines, and perform poorly or fail if users can be organized to perform malicious tasks using crowd-sourcing systems. Through measurements, we have found surprising evidence showing that not only do malicious crowd-sourcing systems exist, but they are rapidly growing in both user base and total revenue. In this paper, we describe a significant effort to study and understand these "crowdturfing" systems in today's Internet. We use detailed crawls to extract data about the size and operational structure of these crowdturfing systems. We analyze details of campaigns offered and performed in these sites, and evaluate their end-to-end effectiveness by running active, non-malicious campaigns of our own. Finally, we study and compare the source of workers on crowdturfing sites in different countries. Our results suggest that campaigns on these systems are highly effective at reaching users, and their continuing growth poses a concrete threat to online communities such as social networks, both in the US and elsewhere.

cs.SI↗

arXiv2012

Multi-scale Dynamics in a Massive Online Social Network

Data confidentiality policies at major social network providers have severely limited researchers' access to large-scale datasets. The biggest impact has been on the study of network dynamics, where researchers have studied citation graphs and content-sharing networks, but few have analyzed detailed dynamics in the massive social networks that dominate the web today. In this paper, we present results of analyzing detailed dynamics in the Renren social network, covering a period of 2 years when the network grew from 1 user to 19 million users and 199 million edges. Rather than validate a single model of network dynamics, we analyze dynamics at different granularities (user-, community- and network- wide) to determine how much, if any, users are influenced by dynamics processes at different scales. We observe in- dependent predictable processes at each level, and find that while the growth of communities has moderate and sustained impact on users, significant events such as network merge events have a strong but short-lived impact that is quickly dominated by the continuous arrival of new users.

cs.SI↗

arXiv2011

Fast and Scalable Analysis of Massive Social Graphs

Graph analysis is a critical component of applications such as online social networks, protein interactions in biological networks, and Internet traffic analysis. The arrival of massive graphs with hundreds of millions of nodes, e.g. social graphs, presents a unique challenge to graph analysis applications. Most of these applications rely on computing distances between node pairs, which for large graphs can take minutes to compute using traditional algorithms such as breadth-first-search (BFS). In this paper, we study ways to enable scalable graph processing on today's massive graphs. We explore the design space of graph coordinate systems, a new approach that accurately approximates node distances in constant time by embedding graphs into coordinate spaces. We show that a hyperbolic embedding produces relatively low distortion error, and propose Rigel, a hyperbolic graph coordinate system that lends itself to efficient parallelization across a compute cluster. Rigel produces significantly more accurate results than prior systems, and is naturally parallelizable across compute clusters, allowing it to provide accurate results for graphs up to 43 million nodes. Finally, we show that Rigel's functionality can be easily extended to locate (near-) shortest paths between node pairs. After a one- time preprocessing cost, Rigel answers node-distance queries in 10's of microseconds, and also produces shortest path results up to 18 times faster than prior shortest-path systems with similar levels of accuracy.

cs.SI↗